context-mcp
Enables teams to query and surface internal documentation programmatically within Claude workflows, reducing context-switching and improving decision velocit…
Self-hosted MCP server that turns your documentation into a searchable knowledge base for AI assistants. Parses MDX, Markdown, and OpenAPI specs, chunks and embeds them with OpenAI or Gemini, stores vectors in Pinecone, and serves search via MCP and REST from a Cloudflare Worker you deploy.
- Ask Claude to search your internal documentation for answers to technical questions quickly.
- Generate summaries of your company's API documentation for new team onboarding.
- Find relevant policy documents and compliance guidelines across your documentation repository.
Enables teams to query and surface internal documentation programmatically within Claude workflows, reducing context-switching and improving decision velocity when technical knowledge is scattered across multiple systems.
Engineering teams managing complex internal docs who need Claude-integrated access to documentation without external API dependencies.
https://github.com/dodopayments/context-mcp
By dodopayments
How to Get It
npx contextmcp init my-docs-mcp # then configure .env (Pinecone + embedding keys), edit config.yaml, npm run reindex, and deploy the cloudflare-worker per README
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Search my internal documentation for answers to technical questions quickly
Trust Signals Auto-scanned
Data & Access
Community Pulse Growing
Discussed on Hacker News
- Show HN: Arbor – A graph-native code indexer in Rust for LLM context (MCP) — Hacker News · 2 pts
- Upgrade Context MCP and Agent for K8s and OSS Projects (Istio, Kafka) — Hacker News · 2 pts
- Cursor MCP — Hacker News · 2 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 53 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 53 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.