Sitereader MCP server
Commit Nov 9, 2026Converts websites and sitemaps into clean Markdown or JSON for RAG and AI applications.
Also known as ByteBlisk/mcp-servers, sitereader
- Stars
- 0
- Tools
- 1
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 9, 2026
- License
- —
What is Sitereader MCP?
Sitereader converts websites and sitemaps into clean Markdown or JSON for RAG and AI applications. It exposes 1 tool, such as byteblisk--sitereader.
Summary generated from the project's README
About Sitereader MCP server
Transforming websites and sitemaps into clean Markdown or JSON for RAG applications is the primary function of this tool. Developers can use it to extract specific data fields by describing them in plain words, making it useful for building knowledge bases or feeding structured information into AI agents. It handles single pages or entire websites to provide the necessary content for retrieval-augmented generation.
Users connect to this remote service via Streamable HTTP using an Apify API token for authentication. It works with MCP clients like Claude Desktop or Cursor by adding the specific endpoint and authorization header to an mcp.json configuration. Because it runs on Apify, there is nothing to install locally. The service operates on a pay-per-use model where every tool specifies its cost, and any failed calls do not incur charges.
What you can do with it
- 1Convert entire websites to MarkdownAn AI agent can crawl a whole site to prepare structured text for a RAG system.
- 2Extract specific data via natural languageA developer can instruct an agent to find specific information on a page using simple descriptions.
Written from the project's README. Every use case is checked against a quote from it.
How to install Sitereader MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Sitereader MCP in Claude Code
$ claude mcp add --transport http sitereader 'https://mcp.apify.com/?tools=byteblisk/sitereader'Install Sitereader MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"sitereader": {
"url": "https://mcp.apify.com/?tools=byteblisk/sitereader"
}
}
}Install Sitereader MCP in VS Code
.vscode/mcp.json
{
"servers": {
"sitereader": {
"type": "http",
"url": "https://mcp.apify.com/?tools=byteblisk/sitereader"
}
}
}Install Sitereader MCP in VS Code CLI
$ code --add-mcp '{"name":"sitereader","type":"http","url":"https://mcp.apify.com/?tools=byteblisk/sitereader"}'Install Sitereader MCP in Codex
$ codex mcp add sitereader --url 'https://mcp.apify.com/?tools=byteblisk/sitereader'Install Sitereader MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.sitereader] url = "https://mcp.apify.com/?tools=byteblisk/sitereader"
Install Sitereader MCP in Gemini CLI
$ gemini mcp add -s user --transport http sitereader 'https://mcp.apify.com/?tools=byteblisk/sitereader'Install Sitereader MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"sitereader": {
"url": "https://mcp.apify.com/?tools=byteblisk/sitereader",
"type": "http"
}
}
}Sitereader MCP tools 1
Read from the server with tools/listbyteblisk--sitereaderActionThis tool sends one HTTP request to the server interface of the Actor "byteblisk/sitereader" and returns the response. Actor description: Website to Markdown for LLMs and RAG, from $1.50 per 1,000 pages. Read single pages, crawl whole sites, map every URL, read PDFs and, with your own Anthropic key, pull AI fields you describe in plain words. Also runs as a fast HTTP API in standby mode and as an MCP server. single-tenant: the first request starts a run in your account, kept for its idle timeout of 300 s. The request is sent once, with no retries and without following redirects. A JSON, text, or XML response body is returned as text, cut at 262144 bytes; other content types are not returned. Operations: - GET /health: Health. - GET /: Root. - GET /v1/read [url:string required, output:string, content:string, unwrap:boolean]: Read Get. - POST /v1/read {url:string required, output:array, content:string, keep:array, drop:array, +16 more}: Read Ep. - POST /v1/discover {url:string required, filter:string, limit:integer, sitemap:boolean, home_links:boolean, +7 more}: Discover Ep. - POST /v1/files {required multipart/form-data body: not supported}: Files Ep. - POST /v1/feed {url:string, kind:string, options:object, access_token:string, id:string, +3 more}: Feed Ep. - POST /v1/explore {url:string required, limit:integer, depth:integer, only_paths:array, skip_paths:array, +10 more}: Explore Ep. - POST /v1/read/batch {urls:array required, webhook, deliver:object, output:array, content:string, +18 more}: Batch Ep. - POST /v1/fields {urls:array required, instructions:string, schema:object, fallback:string, webhook, +4 more}: Fields Ep. - GET /v1/jobs/{job_id} [job_id:string required]: Job Status. - DELETE /v1/jobs/{job_id} [job_id:string required]: Job Cancel. - GET /v1/jobs/{job_id}/errors [job_id:string required]: Job Errors. - GET /v1/account: Account Ep. - GET /v1/recipes: Recipe List. - POST /v1/recipes {example_url:string required, fields:object required, name:string, instructions:string, region, +2 more}: Recipe Add. - GET /v1/recipes/{recipe_id} [recipe_id:string required]: Recipe Get. - DELETE /v1/recipes/{recipe_id} [recipe_id:string required]: Recipe Delete. - POST /v1/recipes/{recipe_id}/run [recipe_id:string required] {urls:array required, region, language:string, robots:string}: Recipe Run. - POST /v1/recipes/{recipe_id}/approve [recipe_id:string required]: Recipe Approve. - GET /v1/watches: Watch List. - POST /v1/watches {urls:array required, every_minutes:integer, only_changes:boolean, include_content:boolean, deliver:object, +7 more}: Watch Add. - GET /v1/watches/{watch_id} [watch_id:string required]: Watch Get. - DELETE /v1/watches/{watch_id} [watch_id:string required]: Watch Delete. - POST /v1/watches/{watch_id}/run [watch_id:string required]: Watch Run.
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablebyteblisk/mcp-servers is public and reachablegithub.com/byteblisk/mcp-servers ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-09github.com/byteblisk/mcp-servers ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model1 tool description and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-11-25 in 1167 ms; tools/list returned 1 tool (HostedMCP test account)Pass
README
View on GitHubByteblisk MCP servers
Three hosted MCP servers for AI agents, running on Apify. Nothing to install: connect over Streamable HTTP with your Apify API token, and pay per use. Every tool states its cost, and failed calls are free.
| Server | What your agent gets | Store page | |
|---|---|---|---|
| Website to Markdown Crawler & API for RAG | Any page or whole site as clean Markdown or JSON, site maps, fields you describe in plain words | apify.com/byteblisk/sitereader | |
| App Store & Google Play Reviews | Reviews from both stores in one format, complaint themes with real quotes, competitor comparison | apify.com/byteblisk/app-reviews-insights | |
| Google Play Scraper API & SERP Rank Checker | Google Play apps, reviews and search, top-100 rank on Google | apify.com/byteblisk/google-play-search-toolkit |
Connect
Endpoints (Streamable HTTP, header Authorization: Bearer <YOUR_APIFY_TOKEN>):
https://byteblisk--sitereader.apify.actor/mcp
https://byteblisk--app-reviews-insights.apify.actor/mcp
https://byteblisk--google-play-search-toolkit.apify.actor/mcp
Claude Desktop, Cursor or any MCP client (mcp.json):
{
"mcpServers": {
"byteblisk-sitereader": {
"url": "https://byteblisk--sitereader.apify.actor/mcp",
"headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
},
"byteblisk-app-reviews": {
"url": "https://byteblisk--app-reviews-insights.apify.actor/mcp",
"headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
},
"byteblisk-google-play-search": {
"url": "https://byteblisk--google-play-search-toolkit.apify.actor/mcp",
"headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
}
}
}
Get a token at console.apify.com/settings/integrations. Prices are on each Store page; Apify's free plan includes monthly credit to try them.
Support
Open an issue on the actor's Store page; we answer every one.
Sitereader MCP questions
How do I add Sitereader MCP to Claude Code?
Run claude mcp add --transport http sitereader 'https://mcp.apify.com/?tools=byteblisk/sitereader' in your terminal. Add --scope user to make it available in every project.
How do I add Sitereader MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Sitereader MCP provide?
It exposes 1 tool, including byteblisk--sitereader.
How do I connect to the server?
You can connect via Streamable HTTP using your Apify API token in the Authorization header.
What formats can the extracted data be in?
The server can provide any page or entire site as clean Markdown or JSON.
Is there a cost for failed calls?
No, failed calls are free of charge.