Récupère des données publiques de réseaux sociaux depuis des plateformes comme Instagram, TikTok, X et YouTube sous forme de JSON propre pour les clients IA.
Aussi connu sous scrapeeverything/mcp, mcp, @scrapeeverything/mcp
- Étoiles
- 3
- Outils
- 42
- Téléchargements, 30 jours
- —
- Dernière version
- 0.1.0
- Dernier commit
- 21 oct. 2026
- Licence
- MIT
Qu'est-ce que Scrape Everything MCP ?
Récupère des données publiques de réseaux sociaux depuis des plateformes comme Instagram, TikTok, X et YouTube sous forme de JSON propre pour les clients IA. Il expose 42 outils, comme get_account, list_scrapers, instagram_profile.
Résumé généré à partir du README du projet
À propos du MCP server Scrape Everything
Scrape Everything fournit une interface pour récupérer des données publiques de réseaux sociaux provenant de plateformes telles qu'Instagram, TikTok, X, YouTube, Facebook, Telegram, Spotify, Pinterest et Twitch. Il convertit le contenu social en un format JSON propre, ce qui permet à des clients IA comme Claude, Cursor, VS Code, Windsurf et d'autres outils compatibles MCP de traiter facilement les informations. Les utilisateurs doivent fournir une clé API Scrape Everything, commençant par le préfixe ssk_live_, pour accéder aux outils de scraping.
Le serveur enregistre dynamiquement les outils en fonction d'un catalogue en direct, ce qui signifie que de nouveaux points de terminaison de scraping apparaissent automatiquement sans nécessiter de mise à jour du package. Il inclut des protections intégrées telles que la troncature des résultats JSON à 100 000 caractères et la fourniture de messages d'erreur clairs incluant les ID de requête et les informations sur les limites de débit. Pour les développeurs ayant besoin d'un accès à distance, le serveur prend en charge un mode HTTP sans état avec des jetons d'authentification configurables et des restrictions d'hôte pour empêcher l'utilisation non autorisée des crédits API.
Ce que vous pouvez faire avec
- 1Extraire des transcriptions YouTubeUn client IA peut utiliser l'outil youtube_transcript pour récupérer le texte d'une vidéo spécifique afin d'en faire un résumé.
- 2Surveiller des profils InstagramUn développeur peut ordonner à un agent de récupérer les détails d'un profil et les photos d'un nom d'utilisateur Instagram spécifique.
- 3Analyser les tendances TikTokVous pouvez demander au serveur de récupérer des publications ou des données musicales sur TikTok pour identifier les contenus tendance.
- 4Vérifier le statut des crédits APILes utilisateurs peuvent vérifier leurs crédits restants et les limites de leur forfait en appelant l'outil de gestion de compte.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer Scrape Everything MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller Scrape Everything MCP dans Claude Code
$ claude mcp add --env 'SCRAPEEVERYTHING_API_KEY=<YOUR_SCRAPEEVERYTHING_API_KEY>' mcp -- npx -y @scrapeeverything/mcpInstaller Scrape Everything MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@scrapeeverything/mcp"
],
"env": {
"SCRAPEEVERYTHING_API_KEY": "<YOUR_SCRAPEEVERYTHING_API_KEY>"
}
}
}
}Installer Scrape Everything MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@scrapeeverything/mcp"
],
"env": {
"SCRAPEEVERYTHING_API_KEY": "<YOUR_SCRAPEEVERYTHING_API_KEY>"
}
}
}
}Installer Scrape Everything MCP dans VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@scrapeeverything/mcp"],"env":{"SCRAPEEVERYTHING_API_KEY":"<YOUR_SCRAPEEVERYTHING_API_KEY>"}}'Installer Scrape Everything MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@scrapeeverything/mcp"
],
"env": {
"SCRAPEEVERYTHING_API_KEY": "<YOUR_SCRAPEEVERYTHING_API_KEY>"
}
}
}
}Installer Scrape Everything MCP dans Codex
$ codex mcp add mcp --env 'SCRAPEEVERYTHING_API_KEY=<YOUR_SCRAPEEVERYTHING_API_KEY>' -- npx -y @scrapeeverything/mcpInstaller Scrape Everything MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@scrapeeverything/mcp"] [mcp_servers.mcp.env] SCRAPEEVERYTHING_API_KEY = "<YOUR_SCRAPEEVERYTHING_API_KEY>"
Installer Scrape Everything MCP dans Gemini CLI
$ gemini mcp add -s user -e 'SCRAPEEVERYTHING_API_KEY=<YOUR_SCRAPEEVERYTHING_API_KEY>' mcp npx -- -y @scrapeeverything/mcpInstaller Scrape Everything MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@scrapeeverything/mcp"
],
"env": {
"SCRAPEEVERYTHING_API_KEY": "<YOUR_SCRAPEEVERYTHING_API_KEY>"
}
}
}
}Démarré par HostedMCP le 16 nov. 2026
Nous avons lancé cette commande pour @scrapeeverything/mcp 0.1.0 dans un conteneur isolé, sans réseau ni clé. Il a répondu et listé 42 outils.
Outils MCP Scrape Everything 42
Lu sur le serveur avec tools/listget_accountLecture seuleShow the current API key's account: email, plan, remaining credits and rate/concurrency limits. Free (no credits).
list_scrapersLecture seuleList the available scrapers (platform, action, tool name, credit cost, parameters). Free. Optionally filter by platform, e.g. "instagram".
instagram_profileLecture seulePublic profile of an Instagram account: bio, avatar, verification/business flags, follower/following/post counts and story-highlight info. Cost: 1 credit per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), biography (string), external_url (string, nullable), profile_pic_url (string, nullable), profile_pic_url_hd (string, nullable), is_private (boolean), is_verified (boolean), is_business_account (boolean), category_name (string, nullable), follower_count (integer, nullable), following_count (integer, nullable), post_count (integer, nullable), has_highlights (boolean, nullable), highlight_count (integer, nullable).
instagram_photosLecture seuleAn Instagram profile plus its most recent posts (up to 60) with type, caption, thumbnail and engagement counts where available. Cost: 2 credits per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), biography (string), external_url (string, nullable), profile_pic_url (string, nullable), profile_pic_url_hd (string, nullable), is_private (boolean), is_verified (boolean), is_business_account (boolean), category_name (string, nullable), follower_count (integer, nullable), following_count (integer, nullable), post_count (integer, nullable), has_highlights (boolean, nullable), highlight_count (integer, nullable), posts (array<object>), posts_fetched (integer), posts_source (string), has_more (boolean).
instagram_postLecture seuleA single Instagram post/reel by URL or shortcode: owner, type, likes, comments, views, caption, timestamp, thumbnail and video URL. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), media_id (string, nullable), link (string), owner_username (string, nullable), type (string), is_video (boolean), product_type (string, nullable), like_count (integer, nullable), like_and_view_counts_disabled (boolean, nullable), comment_count (integer, nullable), view_count (integer, nullable), taken_at (integer, nullable), taken_at_text (string, nullable), caption (string), thumbnail_url (string, nullable), video_url (string, nullable).
instagram_reelLecture seuleA single Instagram reel by URL or shortcode: owner, caption, likes, comments, duration, resolution, audio, cover image and a downloadable MP4 link. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), link (string), media_id (string, nullable), owner_username (string, nullable), caption (string), like_count (integer, nullable), comment_count (integer, nullable), like_and_view_counts_disabled (boolean, nullable), view_count (integer, nullable), taken_at (integer, nullable), taken_at_text (string, nullable), duration_seconds (number, nullable), width (integer, nullable), height (integer, nullable), has_audio (boolean, nullable), audio (object, nullable), thumbnail_url (string, nullable), video_url (string, nullable), video_url_expires_at (string, nullable).
instagram_commentsLecture seuleThe most recent comments (up to 15) on an Instagram post or reel by URL or shortcode: text, time, likes, GIFs and author, plus the post's total comment count. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), link (string), comment_count (integer, nullable), comments (array<object>), comments_fetched (integer), has_more (boolean).
instagram_reelsLecture seuleAn Instagram profile's Reels tab (up to 50 reels) with views, likes, comments, cover image and approximate publish time, plus profile basics. Cost: 2 credits per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), is_verified (boolean), profile_pic_url (string, nullable), follower_count (integer, nullable), reels (array<object>), reels_fetched (integer), has_more (boolean).
instagram_reels_searchLecture seuleFind Instagram reels for a keyword through search-engine results, then open each reel for its owner, caption, likes, comments, views, duration, audio, cover image and MP4 link. Cost: 3 credits per successful call (failed calls are refunded). Returns: query (string), date_posted (string, nullable), page (integer), reels (array<object>), reels_found (integer), reels_fetched (integer), has_more (boolean).
x_profileLecture seulePublic X (Twitter) profile: bio, location, verification, follower/following/tweet/like/media/listed counts, avatar and banner. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), location (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), is_blue_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), tweet_count (integer, nullable), like_count (integer, nullable), media_count (integer, nullable), listed_count (integer, nullable), created_at (string, nullable), profile_image_url (string, nullable), profile_banner_url (string, nullable).
x_postsLecture seuleAn X profile plus its recent timeline (up to 60 tweets incl. pinned, retweets and own replies) with text, media and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), location (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), is_blue_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), tweet_count (integer, nullable), like_count (integer, nullable), media_count (integer, nullable), listed_count (integer, nullable), created_at (string, nullable), profile_image_url (string, nullable), profile_banner_url (string, nullable), posts (array<object>), posts_fetched (integer), has_more (boolean).
x_postLecture seuleA single X post (tweet) by URL or ID: text, author, reply/quote/retweet info, media and engagement counts including views. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), link (string, nullable), text (string), lang (string, nullable), created_at (string, nullable), author_username (string, nullable), is_pinned (boolean), is_retweet (boolean), retweeted_from (string, nullable), is_reply (boolean), in_reply_to (string, nullable), is_quote (boolean), quoted (object, nullable), reply_count (integer, nullable), retweet_count (integer, nullable), quote_count (integer, nullable), like_count (integer, nullable), bookmark_count (integer, nullable), view_count (integer, nullable), media (array<object>).
| get_account | Show the current API key's account: email, plan, remaining credits and rate/concurrency limits. Free (no credits). | Lecture seule |
| list_scrapers | List the available scrapers (platform, action, tool name, credit cost, parameters). Free. Optionally filter by platform, e.g. "instagram". | Lecture seule |
| instagram_profile | Public profile of an Instagram account: bio, avatar, verification/business flags, follower/following/post counts and story-highlight info. Cost: 1 credit per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), biography (string), external_url (string, nullable), profile_pic_url (string, nullable), profile_pic_url_hd (string, nullable), is_private (boolean), is_verified (boolean), is_business_account (boolean), category_name (string, nullable), follower_count (integer, nullable), following_count (integer, nullable), post_count (integer, nullable), has_highlights (boolean, nullable), highlight_count (integer, nullable). | Lecture seule |
| instagram_photos | An Instagram profile plus its most recent posts (up to 60) with type, caption, thumbnail and engagement counts where available. Cost: 2 credits per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), biography (string), external_url (string, nullable), profile_pic_url (string, nullable), profile_pic_url_hd (string, nullable), is_private (boolean), is_verified (boolean), is_business_account (boolean), category_name (string, nullable), follower_count (integer, nullable), following_count (integer, nullable), post_count (integer, nullable), has_highlights (boolean, nullable), highlight_count (integer, nullable), posts (array<object>), posts_fetched (integer), posts_source (string), has_more (boolean). | Lecture seule |
| instagram_post | A single Instagram post/reel by URL or shortcode: owner, type, likes, comments, views, caption, timestamp, thumbnail and video URL. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), media_id (string, nullable), link (string), owner_username (string, nullable), type (string), is_video (boolean), product_type (string, nullable), like_count (integer, nullable), like_and_view_counts_disabled (boolean, nullable), comment_count (integer, nullable), view_count (integer, nullable), taken_at (integer, nullable), taken_at_text (string, nullable), caption (string), thumbnail_url (string, nullable), video_url (string, nullable). | Lecture seule |
| instagram_reel | A single Instagram reel by URL or shortcode: owner, caption, likes, comments, duration, resolution, audio, cover image and a downloadable MP4 link. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), link (string), media_id (string, nullable), owner_username (string, nullable), caption (string), like_count (integer, nullable), comment_count (integer, nullable), like_and_view_counts_disabled (boolean, nullable), view_count (integer, nullable), taken_at (integer, nullable), taken_at_text (string, nullable), duration_seconds (number, nullable), width (integer, nullable), height (integer, nullable), has_audio (boolean, nullable), audio (object, nullable), thumbnail_url (string, nullable), video_url (string, nullable), video_url_expires_at (string, nullable). | Lecture seule |
| instagram_comments | The most recent comments (up to 15) on an Instagram post or reel by URL or shortcode: text, time, likes, GIFs and author, plus the post's total comment count. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `shortcode`. Returns: shortcode (string), link (string), comment_count (integer, nullable), comments (array<object>), comments_fetched (integer), has_more (boolean). | Lecture seule |
| instagram_reels | An Instagram profile's Reels tab (up to 50 reels) with views, likes, comments, cover image and approximate publish time, plus profile basics. Cost: 2 credits per successful call (failed calls are refunded). Returns: id (string), username (string), full_name (string), is_verified (boolean), profile_pic_url (string, nullable), follower_count (integer, nullable), reels (array<object>), reels_fetched (integer), has_more (boolean). | Lecture seule |
| instagram_reels_search | Find Instagram reels for a keyword through search-engine results, then open each reel for its owner, caption, likes, comments, views, duration, audio, cover image and MP4 link. Cost: 3 credits per successful call (failed calls are refunded). Returns: query (string), date_posted (string, nullable), page (integer), reels (array<object>), reels_found (integer), reels_fetched (integer), has_more (boolean). | Lecture seule |
| x_profile | Public X (Twitter) profile: bio, location, verification, follower/following/tweet/like/media/listed counts, avatar and banner. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), location (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), is_blue_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), tweet_count (integer, nullable), like_count (integer, nullable), media_count (integer, nullable), listed_count (integer, nullable), created_at (string, nullable), profile_image_url (string, nullable), profile_banner_url (string, nullable). | Lecture seule |
| x_posts | An X profile plus its recent timeline (up to 60 tweets incl. pinned, retweets and own replies) with text, media and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), location (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), is_blue_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), tweet_count (integer, nullable), like_count (integer, nullable), media_count (integer, nullable), listed_count (integer, nullable), created_at (string, nullable), profile_image_url (string, nullable), profile_banner_url (string, nullable), posts (array<object>), posts_fetched (integer), has_more (boolean). | Lecture seule |
| x_post | A single X post (tweet) by URL or ID: text, author, reply/quote/retweet info, media and engagement counts including views. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), link (string, nullable), text (string), lang (string, nullable), created_at (string, nullable), author_username (string, nullable), is_pinned (boolean), is_retweet (boolean), retweeted_from (string, nullable), is_reply (boolean), in_reply_to (string, nullable), is_quote (boolean), quoted (object, nullable), reply_count (integer, nullable), retweet_count (integer, nullable), quote_count (integer, nullable), like_count (integer, nullable), bookmark_count (integer, nullable), view_count (integer, nullable), media (array<object>). | Lecture seule |
Afficher les 42 outilsAfficher moins d'outils
tiktok_profileLecture seulePublic TikTok profile: nickname, bio, link, verification, follower/following/like/video counts, avatar, region and creation date. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), like_count (integer, nullable), video_count (integer, nullable), profile_image_url (string, nullable), region (string, nullable), created_at (string, nullable).
tiktok_postsLecture seuleA TikTok profile summary plus its newest videos (max 12, from the public embed) with cover, play URL and play count. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), nickname (string), signature (string), is_verified (boolean), is_private (boolean), follower_count (integer, nullable), following_count (integer, nullable), heart_count (integer, nullable), avatar_url (string, nullable), posts (array<object>), posts_fetched (integer), has_more (boolean).
tiktok_videoLecture seuleA single TikTok video by URL or ID: caption, timestamp, like/comment/share/play/save counts, cover, duration, author and music. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `video` OR `id`. Returns: id (string), link (string, nullable), description (string), created_at (string, nullable), like_count (integer, nullable), comment_count (integer, nullable), share_count (integer, nullable), play_count (integer, nullable), save_count (integer, nullable), cover_url (string, nullable), dynamic_cover_url (string, nullable), duration (integer, nullable), author (object), music (object).
tiktok_commentsLecture seuleTop-level comments on a TikTok video by URL or ID: text, likes, reply count, time, pinned and creator-liked flags and the commenter, plus the video's total comment count. Up to 100 comments. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), comment_count (integer, nullable), comments (array<object>), comments_fetched (integer), has_more (boolean).
tiktok_transcriptLecture seuleTimestamped transcript of a TikTok video from its captions (auto-generated or creator-added), with the caption languages available. Pick a language with lang. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), language (string), is_auto_generated (boolean, nullable), available_languages (array<object>), segments (array<object>), text (string), segment_count (integer).
tiktok_musicLecture seuleA TikTok sound by URL or ID: title, artist, duration, original-sound flag, cover, audio URL and how many videos use it, plus the top videos using it (max 12, from the public embed). Cost: 2 credits per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), title (string, nullable), author (string, nullable), album (string, nullable), duration (integer, nullable), is_original (boolean, nullable), cover_url (string, nullable), play_url (string, nullable), video_count (integer, nullable), link (string), videos (array<object>), videos_fetched (integer), has_more (boolean).
tiktok_hashtagLecture seuleTikTok hashtag stats: ID, title, description, total video and view counts, and cover image. Cost: 1 credit per successful call (failed calls are refunded). Returns: id (string, nullable), title (string), description (string), link (string, nullable), video_count (integer, nullable), view_count (integer, nullable), cover_url (string, nullable), is_commerce (boolean).
youtube_profileLecture seuleYouTube channel info by handle, channel ID or URL: title, description, approximate subscriber/video counts, avatar and banner. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `username` OR `channel`. Returns: channel_id (string, nullable), handle (string, nullable), title (string), description (string), keywords (string), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), video_count (integer, nullable), video_count_text (string, nullable), is_family_safe (boolean), channel_url (string, nullable), avatar_url (string, nullable), banner_url (string, nullable), available_countries (integer, nullable).
youtube_videosLecture seuleA YouTube channel summary plus its latest uploads (max 30) with title, approximate views, relative publish time, duration and thumbnail. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `username` OR `channel`. Returns: channel_id (string, nullable), title (string), channel_url (string, nullable), avatar_url (string, nullable), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), videos_fetched (integer), has_more (boolean), videos (array<object>).
youtube_videoLecture seuleA single YouTube video by URL or ID: title, description, exact views, likes, duration, publish date, category, keywords and channel. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `video`. Returns: video_id (string), link (string), title (string), description (string), duration_seconds (integer, nullable), view_count (integer, nullable), like_count (integer, nullable), published_at (string, nullable), category (string, nullable), is_live (boolean), is_family_safe (boolean, nullable), playability (string, nullable), keywords (array<string>), thumbnail_url (string, nullable), channel (object).
youtube_searchLecture seuleSearch YouTube by keyword: videos, Shorts, channels and playlists with views, publish time, duration and channel. Optional type, popularity sort and upload-date filters. Cost: 1 credit per successful call (failed calls are refunded). Returns: query (string), type (string), sort (string), upload_date (string, nullable), results_fetched (integer), has_more (boolean), results (array<object>).
youtube_commentsLecture seuleTop-level comments of a YouTube video by URL or ID, sorted by top or newest: text, author, likes, reply count, pinned and hearted flags, plus the total comment count. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), sort (string), comment_count (integer, nullable), comments_fetched (integer), has_more (boolean), comments (array<object>).
youtube_transcriptLecture seuleTranscript of a YouTube video from its captions: timed segments, joined plain text, chosen language and the list of available caption languages. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), language (string), language_name (string), is_auto_generated (boolean), available_languages (array<object>), segment_count (integer), text (string), segments (array<object>).
youtube_playlistLecture seuleA YouTube playlist by URL or ID: title, description, owner channel, video and view counts, plus its videos (max 100) with views, publish time and duration. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: playlist_id (string), title (string), description (string), channel (object, nullable), video_count (integer, nullable), video_count_text (string, nullable), view_count (integer, nullable), view_count_text (string, nullable), thumbnail_url (string, nullable), url (string), videos_fetched (integer), has_more (boolean), videos (array<object>).
facebook_profileLecture seulePublic Facebook Page/profile metadata from Open Graph tags: name, bio, image and (for Pages) like/follower/talking-about counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: username (string), name (string), like_count (integer, nullable), follower_count (integer, nullable), talking_about_count (integer, nullable), bio (string), profile_url (string), profile_image_url (string, nullable).
telegram_profileLecture seuleTelegram channel/group/bot/user card from t.me: name, type, verification, description, photo and subscriber/member/online counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: username (string), name (string), type (string), is_verified (boolean), description (string), photo_url (string, nullable), subscriber_count (integer, nullable), member_count (integer, nullable), online_count (integer, nullable), monthly_users (integer, nullable), extra_text (string, nullable), link (string), preview_url (string, nullable).
telegram_postsLecture seuleA public Telegram channel's header (counters, description) plus its latest messages (up to 100) with text, media, views and dates. Cost: 2 credits per successful call (failed calls are refunded). Returns: username (string), name (string), is_verified (boolean), description (string), photo_url (string, nullable), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), photo_count (integer, nullable), video_count (integer, nullable), file_count (integer, nullable), link_count (integer, nullable), link (string), posts_fetched (integer), has_more (boolean), posts (array<object>).
telegram_postLecture seuleA single public Telegram channel message by link: text, media, views, date, forward info, link preview and channel info. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `post` OR `username` + `id`. Returns: channel (object), id (integer, nullable), post (string), link (string), type (string), text (string), photo_urls (array<string>), video_url (string, nullable), video_thumb_url (string, nullable), video_duration (string, nullable), view_count (integer, nullable), view_count_text (string, nullable), posted_at (string, nullable), is_forwarded (boolean), forwarded_from (string, nullable), link_preview (object, nullable).
spotify_trackLecture seuleA Spotify track by link/URI/ID: title, artists, duration, release date, explicit flag, cover image and 30-second preview URL. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `track`. Returns: id (string), link (string), title (string), artists (array<object>), duration_ms (integer, nullable), release_date (string, nullable), is_explicit (boolean), is_playable (boolean), has_video (boolean), preview_url (string, nullable), image_url (string, nullable).
spotify_artistLecture seuleA Spotify artist by link/URI/ID: name, image and top tracks (~10) with durations and preview URLs. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `artist`. Returns: id (string), link (string), name (string), image_url (string, nullable), top_tracks (array<object>), top_tracks_count (integer).
spotify_albumLecture seuleA Spotify album by link/URI/ID: title, artists, release date, cover and the full track list. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `album`. Returns: id (string), link (string), title (string), artists_text (string), release_date (string, nullable), is_explicit (boolean), image_url (string, nullable), track_count (integer), tracks (array<object>).
spotify_playlistLecture seuleA public Spotify playlist by link/URI/ID: title, owner, cover, total duration and up to ~50 tracks. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `playlist`. Returns: id (string), link (string), title (string), owner (string), image_url (string, nullable), total_duration_ms (integer, nullable), track_count (integer), tracks (array<object>).
pinterest_profileLecture seulePublic Pinterest profile: name, about, website, verification and follower/following/pin/board/video-pin counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), about (string), website_url (string, nullable), domain (string, nullable), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), pin_count (integer, nullable), board_count (integer, nullable), video_pin_count (integer, nullable), profile_image_url (string, nullable).
pinterest_pinsLecture seuleA Pinterest profile plus its recent pins (up to 50) with images/videos, titles, descriptions, links and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), about (string), website_url (string, nullable), domain (string, nullable), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), pin_count (integer, nullable), board_count (integer, nullable), video_pin_count (integer, nullable), profile_image_url (string, nullable), pins (array<object>), pins_fetched (integer), has_more (boolean).
pinterest_pinLecture seuleA single Pinterest pin by URL or ID: title, description, image/video, outbound link, engagement counts, board and pinner. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), link (string), title (string), description (string), alt_text (string, nullable), dominant_color (string, nullable), image_url (string, nullable), image_width (integer, nullable), image_height (integer, nullable), is_video (boolean), video_url (string, nullable), video_duration_ms (integer, nullable), repin_count (integer, nullable), reaction_count (integer, nullable), comment_count (integer, nullable), favorite_count (integer, nullable), share_count (integer, nullable), outbound_link (string, nullable), outbound_domain (string, nullable), created_at (string, nullable), board_name (string, nullable), board_url (string, nullable), pinner_username (string, nullable), pinner_full_name (string, nullable), pinner_image_url (string, nullable).
pinterest_searchLecture seuleSearch Pinterest pins by keyword: up to 50 results with images/videos, titles, descriptions, outbound links, board and pinner. Cost: 2 credits per successful call (failed calls are refunded). Returns: query (string), pins (array<object>), pins_fetched (integer), has_more (boolean).
pinterest_boardLecture seuleA public Pinterest board: name, description, pin/follower/section counts, owner and cover image, plus its first pins with images, links and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Provide one of: `url` OR `username` + `board`. Returns: board (object), pins (array<object>), pins_fetched (integer), has_more (boolean).
twitch_channelLecture seuleTwitch channel info: display name, description, partner/affiliate status, followers, images and live-stream / last-broadcast details. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), description (string), created_at (string, nullable), is_partner (boolean), is_affiliate (boolean), follower_count (integer, nullable), profile_image_url (string, nullable), banner_image_url (string, nullable), is_live (boolean), stream (object, nullable), last_broadcast (object, nullable).
twitch_videosLecture seuleA Twitch channel's latest videos (past broadcasts, highlights or uploads, up to 50) with title, duration, view count, dates, thumbnail and game. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), type (string), total_count (integer, nullable), videos (array<object>), videos_fetched (integer), has_more (boolean).
twitch_clipsLecture seuleA Twitch channel's most viewed clips for a period (last day, week, month or all time, up to 50) with views, duration, creator, game and the source VOD timestamp. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), period (string), clips (array<object>), clips_fetched (integer), has_more (boolean).
| tiktok_profile | Public TikTok profile: nickname, bio, link, verification, follower/following/like/video counts, avatar, region and creation date. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), biography (string), external_url (string, nullable), is_private (boolean), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), like_count (integer, nullable), video_count (integer, nullable), profile_image_url (string, nullable), region (string, nullable), created_at (string, nullable). | Lecture seule |
| tiktok_posts | A TikTok profile summary plus its newest videos (max 12, from the public embed) with cover, play URL and play count. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), nickname (string), signature (string), is_verified (boolean), is_private (boolean), follower_count (integer, nullable), following_count (integer, nullable), heart_count (integer, nullable), avatar_url (string, nullable), posts (array<object>), posts_fetched (integer), has_more (boolean). | Lecture seule |
| tiktok_video | A single TikTok video by URL or ID: caption, timestamp, like/comment/share/play/save counts, cover, duration, author and music. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `video` OR `id`. Returns: id (string), link (string, nullable), description (string), created_at (string, nullable), like_count (integer, nullable), comment_count (integer, nullable), share_count (integer, nullable), play_count (integer, nullable), save_count (integer, nullable), cover_url (string, nullable), dynamic_cover_url (string, nullable), duration (integer, nullable), author (object), music (object). | Lecture seule |
| tiktok_comments | Top-level comments on a TikTok video by URL or ID: text, likes, reply count, time, pinned and creator-liked flags and the commenter, plus the video's total comment count. Up to 100 comments. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), comment_count (integer, nullable), comments (array<object>), comments_fetched (integer), has_more (boolean). | Lecture seule |
| tiktok_transcript | Timestamped transcript of a TikTok video from its captions (auto-generated or creator-added), with the caption languages available. Pick a language with lang. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), language (string), is_auto_generated (boolean, nullable), available_languages (array<object>), segments (array<object>), text (string), segment_count (integer). | Lecture seule |
| tiktok_music | A TikTok sound by URL or ID: title, artist, duration, original-sound flag, cover, audio URL and how many videos use it, plus the top videos using it (max 12, from the public embed). Cost: 2 credits per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), title (string, nullable), author (string, nullable), album (string, nullable), duration (integer, nullable), is_original (boolean, nullable), cover_url (string, nullable), play_url (string, nullable), video_count (integer, nullable), link (string), videos (array<object>), videos_fetched (integer), has_more (boolean). | Lecture seule |
| tiktok_hashtag | TikTok hashtag stats: ID, title, description, total video and view counts, and cover image. Cost: 1 credit per successful call (failed calls are refunded). Returns: id (string, nullable), title (string), description (string), link (string, nullable), video_count (integer, nullable), view_count (integer, nullable), cover_url (string, nullable), is_commerce (boolean). | Lecture seule |
| youtube_profile | YouTube channel info by handle, channel ID or URL: title, description, approximate subscriber/video counts, avatar and banner. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `username` OR `channel`. Returns: channel_id (string, nullable), handle (string, nullable), title (string), description (string), keywords (string), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), video_count (integer, nullable), video_count_text (string, nullable), is_family_safe (boolean), channel_url (string, nullable), avatar_url (string, nullable), banner_url (string, nullable), available_countries (integer, nullable). | Lecture seule |
| youtube_videos | A YouTube channel summary plus its latest uploads (max 30) with title, approximate views, relative publish time, duration and thumbnail. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `username` OR `channel`. Returns: channel_id (string, nullable), title (string), channel_url (string, nullable), avatar_url (string, nullable), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), videos_fetched (integer), has_more (boolean), videos (array<object>). | Lecture seule |
| youtube_video | A single YouTube video by URL or ID: title, description, exact views, likes, duration, publish date, category, keywords and channel. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `video`. Returns: video_id (string), link (string), title (string), description (string), duration_seconds (integer, nullable), view_count (integer, nullable), like_count (integer, nullable), published_at (string, nullable), category (string, nullable), is_live (boolean), is_family_safe (boolean, nullable), playability (string, nullable), keywords (array<string>), thumbnail_url (string, nullable), channel (object). | Lecture seule |
| youtube_search | Search YouTube by keyword: videos, Shorts, channels and playlists with views, publish time, duration and channel. Optional type, popularity sort and upload-date filters. Cost: 1 credit per successful call (failed calls are refunded). Returns: query (string), type (string), sort (string), upload_date (string, nullable), results_fetched (integer), has_more (boolean), results (array<object>). | Lecture seule |
| youtube_comments | Top-level comments of a YouTube video by URL or ID, sorted by top or newest: text, author, likes, reply count, pinned and hearted flags, plus the total comment count. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), sort (string), comment_count (integer, nullable), comments_fetched (integer), has_more (boolean), comments (array<object>). | Lecture seule |
| youtube_transcript | Transcript of a YouTube video from its captions: timed segments, joined plain text, chosen language and the list of available caption languages. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: video_id (string), language (string), language_name (string), is_auto_generated (boolean), available_languages (array<object>), segment_count (integer), text (string), segments (array<object>). | Lecture seule |
| youtube_playlist | A YouTube playlist by URL or ID: title, description, owner channel, video and view counts, plus its videos (max 100) with views, publish time and duration. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: playlist_id (string), title (string), description (string), channel (object, nullable), video_count (integer, nullable), video_count_text (string, nullable), view_count (integer, nullable), view_count_text (string, nullable), thumbnail_url (string, nullable), url (string), videos_fetched (integer), has_more (boolean), videos (array<object>). | Lecture seule |
| facebook_profile | Public Facebook Page/profile metadata from Open Graph tags: name, bio, image and (for Pages) like/follower/talking-about counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: username (string), name (string), like_count (integer, nullable), follower_count (integer, nullable), talking_about_count (integer, nullable), bio (string), profile_url (string), profile_image_url (string, nullable). | Lecture seule |
| telegram_profile | Telegram channel/group/bot/user card from t.me: name, type, verification, description, photo and subscriber/member/online counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: username (string), name (string), type (string), is_verified (boolean), description (string), photo_url (string, nullable), subscriber_count (integer, nullable), member_count (integer, nullable), online_count (integer, nullable), monthly_users (integer, nullable), extra_text (string, nullable), link (string), preview_url (string, nullable). | Lecture seule |
| telegram_posts | A public Telegram channel's header (counters, description) plus its latest messages (up to 100) with text, media, views and dates. Cost: 2 credits per successful call (failed calls are refunded). Returns: username (string), name (string), is_verified (boolean), description (string), photo_url (string, nullable), subscriber_count (integer, nullable), subscriber_count_text (string, nullable), photo_count (integer, nullable), video_count (integer, nullable), file_count (integer, nullable), link_count (integer, nullable), link (string), posts_fetched (integer), has_more (boolean), posts (array<object>). | Lecture seule |
| telegram_post | A single public Telegram channel message by link: text, media, views, date, forward info, link preview and channel info. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `post` OR `username` + `id`. Returns: channel (object), id (integer, nullable), post (string), link (string), type (string), text (string), photo_urls (array<string>), video_url (string, nullable), video_thumb_url (string, nullable), video_duration (string, nullable), view_count (integer, nullable), view_count_text (string, nullable), posted_at (string, nullable), is_forwarded (boolean), forwarded_from (string, nullable), link_preview (object, nullable). | Lecture seule |
| spotify_track | A Spotify track by link/URI/ID: title, artists, duration, release date, explicit flag, cover image and 30-second preview URL. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `track`. Returns: id (string), link (string), title (string), artists (array<object>), duration_ms (integer, nullable), release_date (string, nullable), is_explicit (boolean), is_playable (boolean), has_video (boolean), preview_url (string, nullable), image_url (string, nullable). | Lecture seule |
| spotify_artist | A Spotify artist by link/URI/ID: name, image and top tracks (~10) with durations and preview URLs. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `artist`. Returns: id (string), link (string), name (string), image_url (string, nullable), top_tracks (array<object>), top_tracks_count (integer). | Lecture seule |
| spotify_album | A Spotify album by link/URI/ID: title, artists, release date, cover and the full track list. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `album`. Returns: id (string), link (string), title (string), artists_text (string), release_date (string, nullable), is_explicit (boolean), image_url (string, nullable), track_count (integer), tracks (array<object>). | Lecture seule |
| spotify_playlist | A public Spotify playlist by link/URI/ID: title, owner, cover, total duration and up to ~50 tracks. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id` OR `playlist`. Returns: id (string), link (string), title (string), owner (string), image_url (string, nullable), total_duration_ms (integer, nullable), track_count (integer), tracks (array<object>). | Lecture seule |
| pinterest_profile | Public Pinterest profile: name, about, website, verification and follower/following/pin/board/video-pin counts. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), about (string), website_url (string, nullable), domain (string, nullable), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), pin_count (integer, nullable), board_count (integer, nullable), video_pin_count (integer, nullable), profile_image_url (string, nullable). | Lecture seule |
| pinterest_pins | A Pinterest profile plus its recent pins (up to 50) with images/videos, titles, descriptions, links and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), full_name (string), about (string), website_url (string, nullable), domain (string, nullable), is_verified (boolean), follower_count (integer, nullable), following_count (integer, nullable), pin_count (integer, nullable), board_count (integer, nullable), video_pin_count (integer, nullable), profile_image_url (string, nullable), pins (array<object>), pins_fetched (integer), has_more (boolean). | Lecture seule |
| pinterest_pin | A single Pinterest pin by URL or ID: title, description, image/video, outbound link, engagement counts, board and pinner. Cost: 1 credit per successful call (failed calls are refunded). Provide one of: `url` OR `id`. Returns: id (string), link (string), title (string), description (string), alt_text (string, nullable), dominant_color (string, nullable), image_url (string, nullable), image_width (integer, nullable), image_height (integer, nullable), is_video (boolean), video_url (string, nullable), video_duration_ms (integer, nullable), repin_count (integer, nullable), reaction_count (integer, nullable), comment_count (integer, nullable), favorite_count (integer, nullable), share_count (integer, nullable), outbound_link (string, nullable), outbound_domain (string, nullable), created_at (string, nullable), board_name (string, nullable), board_url (string, nullable), pinner_username (string, nullable), pinner_full_name (string, nullable), pinner_image_url (string, nullable). | Lecture seule |
| pinterest_search | Search Pinterest pins by keyword: up to 50 results with images/videos, titles, descriptions, outbound links, board and pinner. Cost: 2 credits per successful call (failed calls are refunded). Returns: query (string), pins (array<object>), pins_fetched (integer), has_more (boolean). | Lecture seule |
| pinterest_board | A public Pinterest board: name, description, pin/follower/section counts, owner and cover image, plus its first pins with images, links and engagement counts. Cost: 2 credits per successful call (failed calls are refunded). Provide one of: `url` OR `username` + `board`. Returns: board (object), pins (array<object>), pins_fetched (integer), has_more (boolean). | Lecture seule |
| twitch_channel | Twitch channel info: display name, description, partner/affiliate status, followers, images and live-stream / last-broadcast details. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), description (string), created_at (string, nullable), is_partner (boolean), is_affiliate (boolean), follower_count (integer, nullable), profile_image_url (string, nullable), banner_image_url (string, nullable), is_live (boolean), stream (object, nullable), last_broadcast (object, nullable). | Lecture seule |
| twitch_videos | A Twitch channel's latest videos (past broadcasts, highlights or uploads, up to 50) with title, duration, view count, dates, thumbnail and game. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), type (string), total_count (integer, nullable), videos (array<object>), videos_fetched (integer), has_more (boolean). | Lecture seule |
| twitch_clips | A Twitch channel's most viewed clips for a period (last day, week, month or all time, up to 50) with views, duration, creator, game and the source VOD timestamp. Cost: 1 credit per successful call (failed calls are refunded). Returns: user_id (string, nullable), username (string), display_name (string), period (string), clips (array<object>), clips_fetched (integer), has_more (boolean). | Lecture seule |
Configuration
SCRAPEEVERYTHING_API_KEYRequisSecretScrape Everything API key (ssk_live_...), from https://scrapeeverything.com/dashboard/keys
SCRAPEEVERYTHING_API_URLOverride the API base URL (default https://api.scrapeeverything.com)
SCRAPEEVERYTHING_MCP_AUTH_TOKEN
| Nom | Description | Type |
|---|---|---|
| SCRAPEEVERYTHING_API_KEY | Scrape Everything API key (ssk_live_...), from https://scrapeeverything.com/dashboard/keys | RequisSecret |
| SCRAPEEVERYTHING_API_URL | Override the API base URL (default https://api.scrapeeverything.com) | |
| SCRAPEEVERYTHING_MCP_AUTH_TOKEN | — |
Vérifications automatisées
Exécuté le 12 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleRéussi
- Licence open source (OSI)Réussi
- Commit ou version publiée au cours de l'année écouléeRéussi
- Nom du package non proche d'un package populaireRéussi
- L'endpoint distant utilise HTTPSNon vérifié
- Les outils destructifs sont étiquetésRéussi
- Aucune instruction cachée destinée au modèleRéussi
- Aucun avis critique dans le package ou ses dépendancesRéussi
README
Voir sur GitHubScrape Everything MCP server
An MCP server for Scrape Everything. Public social data as clean JSON. It lets Claude, Cursor, VS Code, Windsurf and any other MCP client fetch public data from Instagram, TikTok, X, YouTube, Facebook, Telegram, Spotify, Pinterest and Twitch.
- One tool per API endpoint. At startup the server reads the live catalog from
GET /v1/scrapersand registers a tool for each scraper (instagram_profile,tiktok_posts,youtube_transcript, ...). New endpoints appear without a package update. - Works offline. If the catalog can't be fetched, the server starts from a bundled snapshot.
- Shows the cost first. Every tool description lists its credit cost and the fields it returns. Failed calls are refunded.
- Gives readable errors. API errors come back as tool errors that keep the error
codeandrequest_id. OnRATE_LIMITEDthe error includes the Retry-After wait. The server never retries on its own. - Keeps results bounded. Results are JSON text, truncated at 100k characters by default, with a note when that happens.
- Sends no telemetry. The only network calls go to the Scrape Everything API.
Get an API key
Create a key at https://scrapeeverything.com/dashboard/keys. Keys look like ssk_live_....
Install
Claude Code
claude mcp add scrapeeverything -e SCRAPEEVERYTHING_API_KEY=ssk_live_... -- npx -y @scrapeeverything/mcp
Claude Desktop
Edit claude_desktop_config.json (Settings, then Developer, then Edit Config):
{
"mcpServers": {
"scrapeeverything": {
"command": "npx",
"args": ["-y", "@scrapeeverything/mcp"],
"env": { "SCRAPEEVERYTHING_API_KEY": "ssk_live_..." }
}
}
}
On Windows, if npx is not found, use "command": "cmd" and "args": ["/c", "npx", "-y", "@scrapeeverything/mcp"].
Cursor
Add this to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
{
"mcpServers": {
"scrapeeverything": {
"command": "npx",
"args": ["-y", "@scrapeeverything/mcp"],
"env": { "SCRAPEEVERYTHING_API_KEY": "ssk_live_..." }
}
}
}
VS Code (GitHub Copilot agent mode)
Add this to .vscode/mcp.json. VS Code prompts for the key and stores it securely:
{
"inputs": [
{ "type": "promptString", "id": "scrapeeverything-key", "description": "Scrape Everything API key", "password": true }
],
"servers": {
"scrapeeverything": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@scrapeeverything/mcp"],
"env": { "SCRAPEEVERYTHING_API_KEY": "${input:scrapeeverything-key}" }
}
}
}
Or from a terminal:
code --add-mcp '{"name":"scrapeeverything","command":"npx","args":["-y","@scrapeeverything/mcp"],"env":{"SCRAPEEVERYTHING_API_KEY":"ssk_live_..."}}'
Windsurf
Add this to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"scrapeeverything": {
"command": "npx",
"args": ["-y", "@scrapeeverything/mcp"],
"env": { "SCRAPEEVERYTHING_API_KEY": "ssk_live_..." }
}
}
}
Self-hosted streamable HTTP
SCRAPEEVERYTHING_API_KEY=ssk_live_... npx -y @scrapeeverything/mcp --http --port 3333
# MCP endpoint: http://127.0.0.1:3333/mcp health: /health
HTTP mode is stateless and accepts POST only. By default it binds to 127.0.0.1 and only accepts loopback Host and Origin headers (127.0.0.1, localhost, [::1]), which blocks DNS rebinding. On loopback, each request can bring its own key with Authorization: Bearer ssk_live_... or x-api-key. If a request has no key, the server uses SCRAPEEVERYTHING_API_KEY.
To listen on any other address, you must set an inbound auth token. Without one the server refuses to start, so it can never act as an open proxy that spends your key:
SCRAPEEVERYTHING_MCP_AUTH_TOKEN="$(openssl rand -hex 32)" \
npx -y @scrapeeverything/mcp --http --host 0.0.0.0 --port 3333 --allowed-host mcp.example.com
- Clients send
Authorization: Bearer <token>. The token is compared in constant time and must be at least 16 characters. - With a token set, each client sends its own Scrape Everything key in
x-api-key. The server'sSCRAPEEVERYTHING_API_KEYis not used as a fallback unless you pass--allow-shared-key. --allowed-host(repeatable, orSCRAPEEVERYTHING_MCP_ALLOWED_HOSTS, comma-separated) restricts theHostheader. Requests that send anOriginheader must match an allowed host or an--allowed-origin(SCRAPEEVERYTHING_MCP_ALLOWED_ORIGINS).- Terminate TLS in front of the server (a reverse proxy) so the token and keys are never sent in clear text.
Configuration
| Variable | Default | Purpose |
|---|---|---|
SCRAPEEVERYTHING_API_KEY |
(none) | API key. Required for scraper tools and get_account. |
SCRAPEEVERYTHING_API_URL |
https://api.scrapeeverything.com |
API base URL. Must be https unless the host is loopback (for local dev, http://127.0.0.1:4001). |
SCRAPEEVERYTHING_MCP_AUTH_TOKEN |
(none) | HTTP mode: inbound bearer token. Required to bind to a non-loopback host. |
SCRAPEEVERYTHING_MCP_ALLOWED_HOSTS |
(none) | HTTP mode: comma-separated extra Host values to accept. |
SCRAPEEVERYTHING_MCP_ALLOWED_ORIGINS |
(none) | HTTP mode: comma-separated extra Origin values to accept. |
SCRAPEEVERYTHING_MCP_MAX_CHARS |
100000 |
Max characters per tool result before truncation. |
SCRAPEEVERYTHING_MCP_SCHEMA_ANYOF |
off | Set it to 1 to emit one_of groups as a top-level anyOf of required sets. |
About one_of: some endpoints accept one of several inputs, for example url or shortcode. Several clients reject a top-level anyOf in tool schemas, Anthropic's API among them. So by default the rule goes in the schema/tool description, and the server checks it before calling the API, which spends no credits. Set SCRAPEEVERYTHING_MCP_SCHEMA_ANYOF=1 if your client supports anyOf.
Tools
| Tool | Credits | Required input |
|---|---|---|
get_account |
0 | (none). Returns email, plan, credits and rate/concurrency limits. |
list_scrapers |
0 | optional platform |
instagram_profile |
1 | username |
instagram_photos |
2 | username |
instagram_post |
1 | one of url or shortcode |
instagram_reel |
1 | one of url or shortcode |
instagram_comments |
1 | one of url or shortcode |
instagram_reels |
2 | username |
instagram_reels_search |
3 | query |
x_profile |
1 | username |
x_posts |
2 | username |
x_post |
1 | one of url or id |
tiktok_profile |
1 | username |
tiktok_posts |
1 | username |
tiktok_video |
1 | one of url or video or id |
tiktok_comments |
1 | one of url or id |
tiktok_transcript |
1 | one of url or id |
tiktok_music |
2 | one of url or id |
tiktok_hashtag |
1 | hashtag |
youtube_profile |
1 | one of username or channel |
youtube_videos |
1 | one of username or channel |
youtube_video |
1 | one of url or id or video |
youtube_search |
1 | query |
youtube_comments |
1 | one of url or id |
youtube_transcript |
1 | one of url or id |
youtube_playlist |
1 | one of url or id |
facebook_profile |
1 | username |
telegram_profile |
1 | username |
telegram_posts |
2 | username |
telegram_post |
1 | one of url or post or username + id |
spotify_track |
1 | one of url or id or track |
spotify_artist |
1 | one of url or id or artist |
spotify_album |
1 | one of url or id or album |
spotify_playlist |
1 | one of url or id or playlist |
pinterest_profile |
1 | username |
pinterest_pins |
2 | username |
pinterest_pin |
1 | one of url or id |
pinterest_search |
2 | query |
pinterest_board |
2 | one of url or username + board |
twitch_channel |
1 | username |
twitch_videos |
1 | username |
twitch_clips |
1 | username |
The live catalog is the source of truth. Ask your assistant to run list_scrapers to see the current list.
Development
npm install
npm run build
npm test
npm run update-catalog # refresh catalog/scrapers.json (honours SCRAPEEVERYTHING_API_URL)
node dist/index.js --help
Inspect the server interactively with npx @modelcontextprotocol/inspector node dist/index.js.
Org and scope placeholders
org.config.json is the one place that records the GitHub org (scrapeeverything) and the npm scope (@scrapeeverything). To change them, run:
npm run apply-org -- --github-org <org> --npm-scope @<scope>
That rewrites package.json (name, mcpName, repository), server.json, smithery.yaml and this README. The MCP Registry name io.github.<org>/mcp must match the GitHub org that publishes it. glama.json lists the GitHub usernames of the Glama maintainers, so put the founder's GitHub username there.
Releasing
- Run
npm version patch(orminor/major). This also syncsserver.json. - Run
git push --follow-tags. - The
release.ymlworkflow publishes to npm with provenance (NPM_TOKENsecret), then publishesserver.jsonto the official MCP Registry through GitHub OIDC.
About Scrape Everything
Scrape Everything is a REST API for public social media data. Send a username, link or ID and get clean, typed JSON from Instagram, TikTok, X, YouTube, Facebook, Telegram, Spotify, Pinterest and Twitch. Pay per successful request with prepaid credits that never expire. New accounts start with 100 free credits. https://scrapeeverything.com
License
MIT © 2026 Scrape Everything
Questions sur Scrape Everything MCP
Comment ajouter Scrape Everything MCP à Claude Code ?
Exécutez claude mcp add --env 'SCRAPEEVERYTHING_API_KEY=<YOUR_SCRAPEEVERYTHING_API_KEY>' mcp -- npx -y @scrapeeverything/mcp dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter Scrape Everything MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Quels outils Scrape Everything MCP fournit-il ?
Il expose 42 outils, dont get_account, list_scrapers, instagram_profile, instagram_photos, instagram_post.
Quelles plateformes de réseaux sociaux puis-je scraper ?
Vous pouvez récupérer des données publiques sur Instagram, TikTok, X, YouTube, Facebook, Telegram, Spotify, Pinterest et Twitch.
Combien coûtent les outils de scraping ?
Chaque description d'outil indique son coût en crédits, et les appels échoués sont remboursés.
Le serveur envoie-t-il des données de télémétrie ?
Non, le serveur n'envoie aucune télémétrie ; les seuls appels réseau effectués sont vers l'API Scrape Everything.
Comment obtenir une clé API ?
Vous pouvez créer une clé API sur le tableau de bord Scrape Everything.