dl4rce/flaiwheel
by Various
MCP Docs Vector - Documentation vectorization and search via MCP
MCP
dl4rce/flaiwheel
Added 1 June 2026
Overview
A Python tool that vectorizes documentation and enables search through the Model Context Protocol (MCP). It converts documentation into vector embeddings and exposes a search interface via MCP, allowing developers to query documentation programmatically.
Best for
Best for
Developers who need to add vector-based documentation search to MCP-enabled workflows
Use cases
- Searching technical documentation using natural language queries
- Integrating documentation search into MCP-compatible applications
- Building a vectorized knowledge base from existing documentation
How to use
Tools exposed
MCP_DOCS_PATHMCP_EMBEDDING_PROVIDERMCP_EMBEDDING_MODELMCP_CHUNK_STRATEGYMCP_RERANKER_ENABLEDMCP_RERANKER_MODELMCP_RRF_KMCP_RRF_VECTOR_WEIGHTMCP_RRF_BM25_WEIGHTMCP_MIN_RELEVANCEMCP_GIT_REPO_URLMCP_GIT_BRANCHMCP_GIT_TOKENMCP_GIT_SYNC_INTERVALMCP_GIT_AUTO_PUSHMCP_WEBHOOK_SECRETMCP_TRANSPORTMCP_SSE_PORTMCP_WEB_PORTall-MiniLM-L6-v2
Tested with
Claude Desktop, Claude Code, Cursor, Continue, VS Code, ChatGPT, GitHub Copilot
Notes
A Python tool that vectorizes documentation and enables search through the Model Context Protocol (MCP). It converts documentation into vector embeddings and exposes a search interface via MCP, allowing developers to query documentation programmatically.
3 stars on GitHub. Last updated 2026-05-22.
Use cases
- Searching technical documentation using natural language queries
- Integrating documentation search into MCP-compatible applications
- Building a vectorized knowledge base from existing documentation
Pros
- Leverages MCP for standardized integration with other tools
- Simple Python implementation for easy customization
- Focused on a specific, useful task without unnecessary complexity
Cons
- Limited to documentation vectorization and search only
- Small community with only 3 GitHub stars
- Requires MCP-compatible infrastructure to be useful
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Leverages MCP for standardized integration with other tools
- Simple Python implementation for easy customization
- Focused on a specific, useful task without unnecessary complexity
Cons
- Limited to documentation vectorization and search only
- Small community with only 3 GitHub stars
- Requires MCP-compatible infrastructure to be useful
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.