Advertise
MCP.so
Sign In

docs-mcp-server MCP Server

@xinlei413

Repository

Basic information

Category

Memory & Knowledge

License

MIT license

Transports

stdio

Author

xinlei413

About docs-mcp-server MCP Server

No overview available yet

#docs-mcp-server#documentation#mcp-server

docs-mcp-server MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "DOC-Server-MCP": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "\\"
      ]
    }
  }
}

docs-mcp-server MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is docs-mcp-server MCP Server?

docs-mcp-server MCP Server is a Model Context Protocol server that fetches, indexes, and searches third-party package documentation. It scrapes content from websites, GitHub, npm, PyPI, or local files, and stores it in a SQLite database with full-text search. It also integrates with OpenRouter API for large language model chat/completions.

How to use docs-mcp-server MCP Server?

Run the server via Docker (recommended) or npx, configured in your MCP client settings (e.g., Claude, Cline, Roo). Set the required OPENAI_API_KEY environment variable and optionally configure embedding models. The server exposes MCP tools for scraping, searching, and managing documentation. Use the CLI to manage the index directly.

Key features of docs-mcp-server MCP Server

  • Versatile scraping: websites, GitHub, npm, PyPI, or local files.
  • Intelligent semantic content splitting for indexing.
  • SQLite with FTS5 for robust full-text search.
  • Asynchronous job handling for scraping and indexing tasks.
  • OpenRouter API integration supporting many large language models.
  • Simple deployment via Docker or npx.

Use cases of docs-mcp-server MCP Server

  • Indexing documentation for libraries across multiple versions.
  • Performing hybrid search (vector + full-text) across package docs.
  • Using an AI assistant to query documentation from indexed packages.
  • Automating documentation updates with background job management.
  • Serving as a documentation retrieval tool within MCP‑enabled applications.

Frequently asked questions

1

How does docs-mcp-server MCP Server index documentation?

It scrapes content from specified URLs, splits it into meaningful chunks, and stores it in a SQLite database using FTS5 for full-text search. Vector embeddings are currently disabled.

2

What embedding providers are supported?

OpenAI, Google Vertex AI, Google Generative AI (Gemini), AWS Bedrock, and Azure OpenAI are supported via environment variables. However, embedding functionality is currently disabled and will throw errors.

3

Can I run docs-mcp-server MCP Server locally without Docker?

Yes, use npx: `npx -y --package=@arabold/docs-mcp-server docs-server`. Node.js must be installed, and the same method should be used for the CLI.

4

What environment variables are required?

`OPENAI_API_KEY` is required. Additional variables depend on the embedding provider (e.g., `AZURE_OPENAI_API_KEY`, `AWS_ACCESS_KEY_ID`, etc.). For OpenRouter chat, set `OPENAI_API_BASE` to the OpenRouter endpoint.

5

Does docs-mcp-server MCP Server support versioned documentation?

Yes, it supports storing and querying documentation for different library versions, including unversioned content, with distinct search capabilities.

Comments

More Memory & Knowledge MCP servers

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

priostack

ideaswave

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

Advertise