vector-mcp 0.0.5

Integrate RAG into AI Agents via MCP Server. Supports multiple Vector database technologies.

Vector Database MCP Server

Version: 0.0.5

This is an MCP Server implementation which allows for a standardized collection management system across vector database technologies.

This was heavily inspired by the RAG implementation of Microsoft's Autogen V1 framework, however, this was changed to an MCP server model instead.

AI Agents can:

• Create collections with documents stored on the local filesystem or URLs
• Add documents to a collection
• Utilize collection for retrieval augmented generation (RAG)
• Delete collection

Supports:

• ChromaDB - 95% Tested
• PGVector - 90% Tested
• Couchbase - 80% Tested
• Qdrant - 80% Tested
• MongoDB - 80% Tested

This repository is actively maintained - Contributions and bug reports are welcome!

Usage:

Using as an MCP Server:

Creating Collection

AI Prompt:

Create a collection called zapdos with the documents in this directory:
/home/user/Documents/Chroma

AI Response:

The collection named "zapdos" has been successfully created or retrieved from the vector database
using the documents in the directory /home/user/Documents/Chroma.
Let me know if you'd like to perform any further actions, such as querying the collection or adding more documents!

Retrieving from Collection

AI Prompt:

Create a collection called zapdos with the documents in this directory:
/home/user/Documents/Chroma

AI Response:

The collection named "zapdos" has been successfully created or retrieved from the vector database
using the documents in the directory /home/user/Documents/Chroma.
Let me know if you'd like to perform any further actions, such as querying the collection or adding more documents!

Deleting Collection

AI Prompt:

Delete the collection called memory

AI Response:

The collection named "memory" has been successfully deleted.
Let me know if you'd like to create a new collection or perform any other actions!

Example:

Use in CLI

Short Flag	Long Flag	Description
-h	--help	See Usage
-h	--host	Host of Vector Database
-p	--port	Port of Vector Database
-d	--path	Path of local Vector Database
-t	--transport	Transport Type (https/stdio)

vector-mcp

Use with AI

Deploy MCP Server as a Service

docker pull knucklessg1/vector-mcp:latest

Modify the compose.yml

services:
  vector-mcp-mcp:
    image: knucklessg1/vector-mcp:latest
    volumes:
      - development:/root/Development
    environment:
      - HOST=0.0.0.0
      - PORT=8001
    ports:
      - 8001:8001

Configure mcp.json

{
  "mcpServers": {
    "repository_manager": {
      "command": "vector-mcp",
      "env": {
        "DATABASE_TYPE": "chromadb",                   // Optional
        "COLLECTION_NAME": "memory",                   // Optional
        "DOCUMENT_DIRECTORY": "/home/user/Documents/"  // Optional
      },
      "timeout": 300000
    }
  }
}

Installation Instructions:

Install Python Package

python -m pip install vector-mcp

PGVector dependencies

python -m pip install vector-mcp[pgvector]

All

python -m pip install vector-mcp[all]

Repository Owners:

Special shoutouts to Microsoft Autogen V1 ♥️