AVS Document Search System

MCP Document Search System

A vector search system for document retrieval using MongoDB Atlas Vector Search and Voyage AI embeddings.

Sample data included is for Atlas Vector Search!

Features

Ingests and chunks markdown documents with hierarchical headers
Generates embeddings using Voyage AI's contextual embeddings API
Stores documents and embeddings in MongoDB with parent-child relationships
Provides a FastMCP server for semantic document search
Supports configurable vector dimensions and chunking strategies

Available MCP Tools

The document search server provides these tools:

search_documents_vector(query: str, limit: int = 5)
- Primary search method using vector similarity
- Returns document chunks with metadata and similarity scores
- Best for semantic/meaning-based queries
search_documents_lexicaly(query: str, limit: int = 1)
- Fallback search using lexical/text matching
- Returns full parent documents with search scores
- Useful when vector search doesn't find good matches
get_parent_document(parent_id: str)
- Retrieves the complete parent document by ID
- Returns original content and file path
- Use after search to get full context for a chunk

Claude Desktop Tool Call

Prerequisites

Python 3.10+
MongoDB Atlas cluster with vector search enabled
Voyage AI API key

Installation

Clone the repository:

git clone https://github.com/patw/avs-document-search.git
cd avs-document-search

Install dependencies:

pip install -r requirements.txt

Create a .env file based on sample.env with your credentials

Usage

Ingest documents in the docs/ directory:

python ingest_docs.py

Run the search server:

python avs-mcp.py

Running the search server won't do much, other than verify your MongoDB URI is correct, you will need to plug this MCP server into an MCP client like Claude Desktop. Here's a sample config:

{
  "mcpServers": {
    "Atlas Vector Search Docs": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "fastmcp, pymongo, requests",
        "fastmcp",
        "run",
        "<path to>/avs-docs-mcp/avs-mcp.py"
      ]
    }
  }
}

Configuration

Copy sample.env to .env and Edit to configure:

MongoDB connection string
Database and collection names
Voyage AI API key
Vector dimensions (256 default)

Future Improvements

Implement hybrid search combining vector and text search using $rankFusion (when MongoDB 8.1 is GA on Atlas)
Support additional file formats (PDF, Word, etc.) with Docling

Contributing

Pull requests are welcome! For major changes, please open an issue first.

Author

Pat Wendorf
pat.wendorf@mongodb.com
GitHub: patw

License

MIT

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A vector search system that enables semantic retrieval of document chunks using MongoDB Atlas Vector Search and Voyage AI embeddings, allowing users to search documents by meaning rather than just keywords.

Related MCP Servers

mcp-ragdocs
hannesrudolph
A
security
A
license
A
quality
An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context
Last updated -
7
30
211
TypeScript
MIT License
RAG Documentation MCP Server
rahulretnan
-
security
F
license
-
quality
Enables AI assistants to enhance their responses with relevant documentation through a semantic vector search, offering tools for managing and processing documentation efficiently.
Last updated -
30
37
TypeScript
Qdrant Retrieve MCP Server
gergelyszerovay
-
security
A
license
-
quality
Enables semantic search across multiple Qdrant vector database collections, supporting multi-query capability and providing semantically relevant document retrieval with configurable result counts.
Last updated -
46
TypeScript
MIT License
RAG Documentation MCP Server
jumasheff
-
security
A
license
-
quality
Provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.
Last updated -
30
TypeScript
MIT License

View all related MCP servers