Docfork
An MCP server that gives AI agents access to up-to-date documentation from 10,000+ open-source projects. Uses a 'Cabinet' system to lock documentation queries to a specific tech stack (e.g., Next.js 16 + Drizzle ORM + Better Auth), filtering out irrelevant results. Supports both remote HTTP and local stdio transports, with team sharing of Cabinets and API keys. Exposes two MCP tools: query_docs for documentation search and fetch_url for full content retrieval.
Best When
You are coding with an AI assistant and need accurate, current documentation scoped to your exact tech stack, especially when working in a team that wants standardized library references.
Avoid When
You primarily use private/internal libraries, need more than 1,000 requests/month on the free tier, or your tech stack uses obscure libraries unlikely to be in their collection.
Use Cases
- • Getting current documentation for specific library versions during AI-assisted coding
- • Locking an AI coding assistant to your exact tech stack to prevent irrelevant suggestions
- • Team-wide standardization of which libraries and versions agents reference
- • Preventing AI hallucination of deprecated or nonexistent APIs
- • Augmenting 40+ code editors and AI assistants with live documentation
Not For
- • Private or internal documentation (public open-source libraries only)
- • Libraries not in Docfork's 10,000+ curated collection
- • Guaranteed documentation accuracy (community-curated with submission reviews)
- • High-volume production use without a paid plan (1,000 free requests/month)
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Docfork.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-01.