Context.dev MCP server
2026년 11월 12일 커밋Enables Cursor to perform live web searches, scraping, crawling, and structured data extraction via MCP.
다른 이름 context-dot-dev/cursor-plugin
- 스타
- 11
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 12일
- 라이선스
- MIT
Context.dev MCP란?
Context.dev은(는) MCP server입니다. Enables Cursor to perform live web searches, scraping, crawling, and structured data extraction via MCP.
프로젝트 README에서 생성된 요약
Context.dev MCP server 정보
Providing Cursor with live web access for research and data extraction is the primary function of this plugin. Developers can use it to perform web searches, scrape specific URLs for markdown or JSON, and crawl multiple pages for discovery. It also handles document parsing for PDFs and Office files, alongside specialized brand intelligence tools that retrieve logos, fonts, and design systems.
Setup involves installing the plugin from the Cursor Marketplace and enabling the context server within Cursor Settings. Authentication is handled via OAuth, meaning you sign in through the Context.dev interface rather than manually copying API keys into your client. The server provides 42 typed tools, including capabilities for recurring website monitors and large asynchronous batches of up to 25,000 URLs.
Users can interact with the system through specific commands like /scrape-url or /search-web. While the MCP server handles interactive tasks through OAuth, developers building their own applications can use the Context.dev REST API or SDKs by managing a CONTEXT_DEV_API_KEY in their environment variables.
활용 사례
- 1Perform live web researchAsk the AI to find the latest product announcements from a specific company and provide the source links.
- 2Extract structured data from websitesRequest a summary of pricing plans by scraping a specific webpage.
- 3Retrieve brand identity assetsGet a complete brand profile including logos, colors, and social media profiles for a specific domain.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
README
GitHub에서 보기Context.dev for Cursor
The official Context.dev plugin for Cursor. Give Cursor reliable access to the live web: search, company news, scraping, crawling, structured extraction, document parsing, brand intelligence, screenshots, recurring monitors, account usage, and large asynchronous batches.
Install and connect
- Install Context.dev from the Cursor Marketplace.
- Open Cursor Settings → Tools & MCP and enable the
contextserver. - Select Connect or Authenticate, then sign in to Context.dev and approve access.
The plugin connects to https://mcp.context.dev/mcp with OAuth. You do not need to copy an API key into Cursor.
If an older installation still shows a legacy Context.dev server, remove that manual server and reinstall or refresh the plugin.
Try it
Ask Cursor:
Use Context.dev to search for Stripe's latest official product announcements and cite the source URLs.
Use Context.dev to scrape https://www.context.dev/pricing and summarize the plans.
Use Context.dev to retrieve the brand profile for linear.app, including its logo, colors, fonts, and social profiles.
Cursor automatically selects the appropriate Context.dev tool. Tool calls require normal Cursor approval, and account-changing tools such as monitor, batch, cancel, update, and delete operations should only run when explicitly requested.
Included
| Component | What it provides |
|---|---|
| MCP server | The production Context.dev MCP with 42 direct, typed tools and OAuth |
| Skills | Focused MCP workflows, direct API guidance, Cursor connection help, and Logo Link integration |
| Commands | /brand-colors, /scrape-url, /search-web, and /extract-web-data |
| Rules | Routes live-web tasks to the right Context.dev tool and keeps credentials out of client code |
Skill catalog
| Skill | When Cursor uses it |
|---|---|
context-search |
Live web research and source discovery |
context-scrape |
Markdown, HTML, images, screenshots, or structured JSON from one known URL |
context-crawl |
URL discovery and focused multi-page crawling |
context-extract |
Schema-shaped JSON from a known webpage |
context-parse |
PDFs, Office files, images, and other local document bytes |
context-brand |
Brand profiles, design systems, fonts, and industry codes |
context-monitor |
Recurring website-change detection and history |
context-batches |
Large asynchronous scrape and crawl jobs |
context-dev |
Building directly with the Context.dev REST API or SDKs |
connect-context-dev |
OAuth setup and MCP troubleshooting |
logolink |
Safe dynamic company logos in frontend applications |
MCP tool catalog
| Group | Tools |
|---|---|
| Parse | parse-document |
| Web | web-scrape, web-map, web-crawl, web-search, web-answers |
| Company and people | get-news-search, get-brand, brand-retrieve-unified, brand-search, people-enrich, web-styleguide |
| Batches | submit-batch, list-batches, get-batch, get-batch-results, cancel-batch, delete-batch |
| Monitors | create-monitor, list-monitors, get-monitor, update-monitor, delete-monitor, get-monitor-limits, list-monitor-credit-usage, run-monitor-now, list-monitor-runs, get-monitor-run, list-account-runs, list-monitor-changes, get-change, list-changes, rotate-monitor-webhook-secret |
| Webhooks | list-webhook-deliveries, get-webhook-delivery, list-webhook-delivery-attempts, retry-webhook-delivery |
| Account and feedback | get-usage, get-usage-history, list-logs, get-log, submit-feedback |
For a known page, use web-scrape with formats: { markdown: true }. Use web-search when the URL is unknown, web-crawl for a focused multi-page request, and submit-batch for up to 25,000 URLs or a large asynchronous crawl.
Building with the Context.dev API
OAuth connects Cursor to the MCP server. If you are writing application code that calls the Context.dev REST API or SDK directly, create an API key in the Context.dev dashboard and keep it in a server-side CONTEXT_DEV_API_KEY environment variable. Never put a private API key in browser code or commit it to source control.
The bundled context-dev API reference is synchronized from docs.context.dev/skill.md. Its Cursor activation description is narrowed to direct API and SDK development, while the focused OAuth skills route interactive work through the public production MCP tools.
Local development
Validate the repository and confirm that the bundled API skill matches the published documentation:
node scripts/validate-plugin.mjs
node scripts/sync-skill.mjs --check
node scripts/check-mcp-oauth.mjs
Load the plugin from this checkout using Cursor's documented local-plugin directory:
mkdir -p ~/.cursor/plugins/local
rsync -a --delete --exclude '.git/' ./ ~/.cursor/plugins/local/context-dev/
Then run Developer: Reload Window in Cursor and verify that the context MCP server, four commands, eleven skills, and two rules appear. A copied directory is used because current Cursor builds reject local-plugin symlinks whose targets are outside ~/.cursor/plugins/local.
Links
License
MIT — see LICENSE.
Context.dev MCP 질문
How do I connect Context.dev to Cursor?
Install the plugin from the Cursor Marketplace, enable the 'context' server in Cursor Settings, and then select Connect or Authenticate to sign in via OAuth.
Do I need an API key to use the plugin in Cursor?
No, the plugin uses OAuth for connection, so you do not need to manually copy an API key into Cursor.
Can I scrape large batches of URLs?
Yes, you can use the submit-batch tool for up to 25,000 URLs or for large asynchronous crawl jobs.