MCPgee
MCPgee
MCPgeeMCPgee

MCP Documentation

v1.0.0•Knowledge & Memory•stable

MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • I

documentsgeminiknowledge-basemcp-servermodel-context-protocol
Share:
315
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is MCP Documentation?

MCP Documentation is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp documentation server - bridge the ai knowledge gap. ✨ features: document management • gemini integration • ai-powered semantic search • file uploads • smart chunking • multilingual support • zero-...

MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • I

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Fe

Use Cases

Build AI-powered documentation search.
Upload and manage documents.
Access semantic search features.
andrea9293

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx mcp-documentation

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Documentation

MCP Documentation Server bridges the AI knowledge gap by letting Claude and other MCP clients manage, search, and query a private documentation library. It supports adding documents by text or file upload (PDF, Markdown, plain text), performs hybrid full-text and semantic vector search using local embeddings, optionally integrates Google Gemini for AI-powered deep analysis, and ships a built-in web dashboard at localhost:3080 for drag-and-drop document management—all with zero mandatory API keys.

Prerequisites

  • Node.js 18 or later and npx installed
  • Claude Desktop or another MCP-compatible client
  • Google Gemini API key (optional, only for AI-powered search and analysis)
  • Sufficient disk space for the local document database (default: ~/.mcp-documentation-server)
1

Add the server to Claude Desktop config

Open your Claude Desktop configuration file and add the mcp-documentation-server entry. The package is published under the scoped name `@andrea9293/mcp-documentation-server`.

{
  "mcpServers": {
    "documentation": {
      "command": "npx",
      "args": ["-y", "@andrea9293/mcp-documentation-server"]
    }
  }
}
2

Configure optional environment variables

Add environment variables to the server entry if you want Gemini-powered AI search, a custom storage directory, or a different web UI port. All are optional.

{
  "mcpServers": {
    "documentation": {
      "command": "npx",
      "args": ["-y", "@andrea9293/mcp-documentation-server"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key",
        "MCP_BASE_DIR": "/path/to/custom/storage",
        "MCP_EMBEDDING_MODEL": "Xenova/all-MiniLM-L6-v2",
        "START_WEB_UI": "true",
        "WEB_PORT": "3080"
      }
    }
  }
}
3

Restart Claude Desktop

Save the config file and restart Claude Desktop. On first launch the server downloads the local embedding model (~25 MB). The web dashboard will be available at http://localhost:3080.

4

Add your first document via the web UI

Open http://localhost:3080 in your browser. Drag and drop a PDF, Markdown, or text file into the upload area, or paste text directly. The server chunks and indexes it automatically.

5

Add documents and search via Claude

You can also add and search documents directly through Claude. Ask Claude to add a document, search for content, or use the REST API for programmatic access.

# REST API example — add a document
curl -X POST http://127.0.0.1:3080/api/documents \
  -H "Content-Type: application/json" \
  -d '{"title": "API Guide", "content": "...full text..."}'

# Search across all documents
curl -X POST http://127.0.0.1:3080/api/search-all \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication flow", "limit": 5}'

MCP Documentation Examples

Client configuration

Claude Desktop config with Gemini AI search enabled. Remove the GEMINI_API_KEY line to run in local-only mode.

{
  "mcpServers": {
    "documentation": {
      "command": "npx",
      "args": ["-y", "@andrea9293/mcp-documentation-server"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key",
        "WEB_PORT": "3080"
      }
    }
  }
}

Prompts to try

Example prompts for managing and searching your documentation library through Claude.

- "Add this text as a document titled 'Auth Flow': [paste content]"
- "Search my documentation for anything related to OAuth token refresh"
- "List all documents I've added so far"
- "Find the section in my API docs that explains rate limiting"
- "Use Gemini to analyze all documents and give me a summary of the authentication patterns described"

Troubleshooting MCP Documentation

Server fails to start — 'Cannot find module' errors with npx

Clear the npx cache with `npx clear-npx-cache` and retry. Ensure you are using Node.js 18 or later (`node --version`). The scoped package name `@andrea9293/mcp-documentation-server` must be used exactly as written.

AI-powered search returns errors about Gemini

Verify your GEMINI_API_KEY is valid and has access to the Gemini embedding and generation APIs. Obtain a key at aistudio.google.com. If you do not have a key, remove the env var — the server falls back to local vector search automatically.

Web UI is not accessible at localhost:3080

Check that no other process is using port 3080 (`lsof -i :3080` on macOS/Linux). Change the port by setting `WEB_PORT` to a free port in the server's env config. Set `START_WEB_UI` to `false` if you want to run headlessly.

Frequently Asked Questions about MCP Documentation

What is MCP Documentation?

MCP Documentation is a Model Context Protocol (MCP) server that mcp documentation server - bridge the ai knowledge gap. ✨ features: document management • gemini integration • ai-powered semantic search • file uploads • smart chunking • multilingual support • zero-setup 🎯 perfect for: new frameworks • api docs • i It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Documentation?

Follow the installation instructions on the MCP Documentation GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Documentation?

MCP Documentation works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Documentation free to use?

Yes, MCP Documentation is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

MCP Documentation Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to MCP Documentation? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "mcp-documentation": { "command": "npx", "args": ["-y", "mcp-documentation"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Documentation?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides