DataBridge MCP Server

DataBridge MCP servers enable AI models to interact with local databases for contextual information, supporting persistent storage and unified access to ML services.

GitHub starsnpm versionnpm downloads

Overview

The MCP DataBridge Server integrates with DataBridge to enable ingestion and retrieval of contextual information from a local database, supporting persistent storage for AI applications. It implements the Model Context Protocol (MCP), enabling connections to different ML services through a unified interface.

Developed by:

DataBridge

Key Features

🗄️

Contextual Information Ingestion

Ingest and manage contextual data from local databases for AI models.

🔍

Efficient Data Retrieval

Retrieve relevant contextual information quickly for AI applications.

🔗

Unified ML Service Interface

Connect to various ML services through a single, standardized interface.

💾

Persistent Storage Support

Utilize local databases for persistent storage of AI-related data.

Available Tools

Quick Reference

ToolPurposeCategory
ingest_dataIngest contextual informationWrite
retrieve_dataRetrieve contextual informationRead
list_ml_servicesList available ML servicesDiscovery

Detailed Usage

ingest_data

Ingest contextual data into the local database.

use_mcp_tool({
  server_name: "databridge",
  tool_name: "ingest_data",
  arguments: {
    data: {
      "document_id": "doc123",
      "content": "This is the content of the document."
    },
    collection: "documents"
  }
});
retrieve_data

Retrieve contextual data from the local database.

use_mcp_tool({
  server_name: "databridge",
  tool_name: "retrieve_data",
  arguments: {
    query: "document_id = 'doc123'",
    collection: "documents"
  }
});
list_ml_services

List available ML services connected through the DataBridge MCP server.

use_mcp_tool({
  server_name: "databridge",
  tool_name: "list_ml_services",
  arguments: {}
});

Installation

{
  "mcpServers": {
    "databridge": {
      "command": "python",
      "args": [
        "-m",
        "databridge.mcp"
      ]
    }
  }
}

Prerequisites:

Ensure Python 3.8 or higher and uv or pip are installed. Install with uv: uv venv && source .venv/bin/activate && uv pip install mcp-server Install with pip: pip install mcp-server

Sources