MCP Documentation Server

What is MCP Documentation Server about?

MCP Documentation Server offers a TypeScript‑based solution that lets you upload documents, automatically split them into context‑aware chunks, embed those chunks with high‑quality models, and perform fast semantic search. All data is kept in a local ~/.mcp‑documentation‑server/ directory, making it ideal for private knowledge bases, API docs, or internal guides.

How to use MCP Documentation Server?

Start the server (recommended):

npx @andrea9293/mcp-documentation-server

Add it to your MCP client configuration (e.g., Claude Desktop):

{
  "mcpServers": {
    "documentation": {
      "command": "npx",
      "args": ["-y", "@andrea9293/mcp-documentation-server"],
      "env": { "MCP_EMBEDDING_MODEL": "Xenova/all-MiniLM-L6-v2" }
    }
  }
}

Interact via tools such as add_document, search_documents, get_context_window, list_documents, etc., using the MCP client or direct HTTP calls.

Key Features

Document management (add, list, retrieve, delete) with metadata support
AI‑powered semantic search using configurable embedding models
Intelligent chunking and context‑window retrieval for richer answers
Multilingual embeddings for non‑English content
Simple file upload workflow for .txt, .md, and .pdf files
Zero‑setup local storage, no external database required
Fast start via npx and optional global install

Use Cases

Centralized internal knowledge base for engineering teams
API documentation portal with natural‑language search
On‑premise reference library for confidential projects
Multilingual guide repository for global products
Rapid prototype of a chatbot that answers from your own docs

FAQ

Q: Do I need an API key? A: No external API key is required; the server runs entirely locally. You only need to set MCP_EMBEDDING_MODEL if you want a model other than the default.

Q: Can I change the embedding model after adding documents? A: Changing the model invalidates existing embeddings. Re‑add or re‑process all documents after switching models.

Q: How are large PDFs handled? A: Text is extracted (no OCR). Split into chunks automatically; processing time depends on file size.

Q: Where are the files stored? A: In ~/.mcp-documentation-server/ under data/ for JSON documents and uploads/ for raw files.

Q: Is it cross‑platform? A: Yes. Runs on any system with Node.js (Linux, macOS, Windows).

A TypeScript-based Model Context Protocol (MCP) server that provides document management and semantic search capabilities. Upload documents, search them with AI embeddings, and integrate seamlessly with MCP clients like Claude Desktop.

Demo Video

Quick Start

1. Install and Run

# Run directly with npx (recommended)
npx @andrea9293/mcp-documentation-server

2. Configure MCP Client

Add to your MCP client configuration (e.g., Claude Desktop):

{
  "mcpServers": {
    "documentation": {
      "command": "npx",
      "args": [
        "-y",
        "@andrea9293/mcp-documentation-server"
      ],
      "env": {
        "MCP_EMBEDDING_MODEL": "Xenova/all-MiniLM-L6-v2"
      }
    }
  }
}

3. Start Using

Add documents: Upload text/markdown files or add content directly
Search documents: Use semantic search to find relevant information
Manage content: List, retrieve, and organize your documents

Features

📄 Document Management - Add, list, retrieve, and delete documents with metadata
🔍 Semantic Search - AI-powered search using embeddings
🧠 Intelligent Chunking - Documents are automatically split into context-aware chunks for better search accuracy and context retrieval
🧩 Context Window Retrieval - Retrieve a window of chunks around a relevant chunk to get more context for your queries
� LLM Guidance - The search tool provides hints to LLMs on how to use context windowing for better answers
📁 File Upload - Drop .txt/.md/.pdf files in uploads folder for processing
🗑️ Document Deletion - Clean removal of documents and their chunks
🌍 Multilingual - Supports multiple languages with quality embeddings
💾 Local Storage - All data stored locally in ~/.mcp-documentation-server/ directory
⚡ Fast Setup - No database required, works out of the box

Available Tools

Tool	Description
`add_document`	Add a document with title, content, and metadata
`search_documents`	Search for chunks within a specific document. Returns a hint for LLMs on how to retrieve more context.
`get_context_window`	Returns a window of chunks around a central chunk for a document
`list_documents`	List all documents with their metadata
`get_document`	Retrieve a complete document by ID
`delete_document`	Delete a document by ID (removes all associated chunks)
`get_uploads_path`	Get path to uploads folder
`list_uploads_files`	List files in uploads folder
`process_uploads`	Process uploaded files into documents

Usage Examples

Adding a Document

{
  "tool": "add_document",
  "arguments": {
    "title": "Python Basics",
    "content": "Python is a high-level programming language...",
    "metadata": {
      "category": "programming",
      "tags": ["python", "tutorial"]
    }
  }
}

Searching Documents

{
  "tool": "search_documents",
  "arguments": {
    "document_id": "doc-123",
    "query": "variable assignment",
    "limit": 5
  }
}

Retrieving Context Window

{
  "tool": "get_context_window",
  "arguments": {
    "document_id": "doc-123",
    "chunk_index": 5,
    "before": 2,
    "after": 2
  }
}

Deleting a Document

{
  "tool": "delete_document",
  "arguments": {
    "id": "doc-123"
  }
}

File Upload Workflow

Get uploads path: get_uploads_path (~/.mcp-documentation-server/uploads/)
Place your .txt/.md/.pdf files in that folder
Process files: process_uploads
Search the processed documents

Supported file types:

.txt - Plain text files
.md - Markdown files
.pdf - PDF files (text extraction, no OCR)

Configuration

Data Storage

All documents and uploads are stored locally in:

~/.mcp-documentation-server/
├── data/      # Document storage (JSON files)
└── uploads/   # Files to process (.txt, .md, .pdf)

Embedding Models

Set via MCP_EMBEDDING_MODEL environment variable:

Xenova/all-MiniLM-L6-v2 (default) - Fast, good quality (384 dimensions)
Xenova/paraphrase-multilingual-mpnet-base-v2 (recommended) - Best quality, multilingual (768 dimensions)

The system automatically manages the correct embedding dimension for each model. Embedding providers expose their dimension via getDimensions().

⚠️ Important: Changing models requires re-adding all documents as embeddings are incompatible.

Installation Options

NPX (Recommended)

npx @andrea9293/mcp-documentation-server

Global Installation

npm install -g @andrea9293/mcp-documentation-server
mcp-documentation-server

From Source

git clone https://github.com/andrea9293/mcp-documentation-server.git
cd mcp-documentation-server
npm install
npm run build
npm start

Best Practices

Document Organization

Use descriptive titles for easy identification
Add relevant metadata (tags, categories) for better organization
Keep documents focused on specific topics for better search accuracy

Search Optimization

Use specific, descriptive search queries
Combine keywords related to your topic
Start with broader queries, then refine with more specific terms
After finding relevant chunks with search_documents, use get_context_window to retrieve additional context around those chunks. You can call get_context_window multiple times until you have enough context to answer your question.

Performance Tips

Process large files during off-peak hours (initial embedding creation)
Use smaller embedding models for faster performance if quality is acceptable
Regularly clean up unused documents to maintain performance

Troubleshooting

Timeout on First Use

Cause: Embedding models download on first use (~420MB for best model)
Solution: Wait for background download to complete, or use smaller model initially

Search Results Issues

Cause: Mixed embedding models in same dataset
Solution: Stick to one model or re-add all documents after switching

Development

# Development server with hot reload
npm run dev

# Build and test
npm run build

# Inspect tools with web UI
npm run inspect

Contributing

Fork the repository
Create feature branch: git checkout -b feature/name
Follow Conventional Commits for messages
Submit pull request

License

MIT - see LICENSE file

Support

Built with FastMCP and TypeScript 🚀

MCP Documentation Server