docs-mcp-server
If you are the rightful owner of docs-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Docs MCP Server is a tool that provides a personal, always-current knowledge base for AI by indexing third-party documentation from various sources, offering version-aware search tools via the Model Context Protocol (MCP).
The Docs MCP Server addresses the common issues faced by AI coding assistants, such as outdated documentation and hallucinations, by providing a personal, always-current knowledge base. It indexes third-party documentation from various sources like websites, GitHub, npm, PyPI, and local files, offering powerful, version-aware search tools via the Model Context Protocol (MCP). This ensures that AI agents have access to the latest official documentation, improving the quality and reliability of generated code and integration details. The server is free, open-source, runs locally for privacy, and integrates seamlessly into development workflows. It helps overcome challenges like stale knowledge, code hallucinations, version ambiguity, and verification overhead by providing up-to-date context, delivering version-specific answers, reducing hallucinations, and boosting productivity.
Features
- Accurate & Version-Aware AI Responses: Provides up-to-date, version-specific documentation to reduce AI hallucinations and improve code accuracy.
- Broad Source Compatibility: Scrapes documentation from websites, GitHub repos, package manager sites (npm, PyPI), and local file directories.
- Advanced Search & Processing: Intelligently chunks documentation semantically, generates embeddings, and combines vector similarity with full-text search.
- Flexible Embedding Models: Supports various providers including OpenAI, Google Gemini/Vertex AI, Azure OpenAI, and AWS Bedrock.
- Local & Private: Runs entirely on your machine, ensuring data and queries remain private.
