MindsDB MCP server

MindsDB is a powerful solution for building AI applications that can seamlessly connect with various enterprise data sources. It functions as a federated query engine that organizes your scattered data while answering your questions through AI, whether your data is stored in SaaS applications, databases, or data warehouses.

Installation Options

Using Docker Desktop

This is the fastest and recommended way to get started:

1. Visit the Docker Desktop installation guide
2. Follow the step-by-step instructions to install and configure MindsDB

Using Docker

For more flexibility and customization:

docker pull mindsdb/mindsdb
docker run -p 47334:47334 mindsdb/mindsdb

Detailed instructions are available in the Docker installation guide.

Using PyPI

If you want to install from Python package:

pip install mindsdb

For more detailed PyPI installation instructions, visit the PyPI installation guide.

Connecting Data Sources

MindsDB supports hundreds of data sources. Here's an example of connecting to a Postgres database:

-- Connect to demo postgres DB
CREATE DATABASE demo_postgres_db
WITH ENGINE = "postgres",
PARAMETERS = {
  "user": "demo_user",
  "password": "demo_password",
  "host": "samples.mindsdb.com",
  "port": "5432",
  "database": "demo",
  "schema": "demo_data"
};

Once connected, you can manipulate your data using standard SQL commands to combine, filter, and transform it.

Building Knowledge Bases

Knowledge Bases in MindsDB are autonomous RAG (Retrieval-Augmented Generation) systems that can process both structured and unstructured data.

Creating a Knowledge Base for Amazon Reviews

-- First create a knowledge base
CREATE KNOWLEDGE_BASE mindsdb.reviews_kb;

-- Insert Amazon reviews data into the knowledge base
INSERT INTO mindsdb.reviews_kb (
  SELECT review as content FROM demo_pg_db.amazon_reviews
);

-- Check the status of your data loading
SELECT * FROM information_schema.knowledge_bases;

-- Query the content of the knowledge base
SELECT * FROM mindsdb.reviews_kb;

Searching Your Knowledge Base

Via SQL

Once your knowledge base is loaded, you can search for specific information:

-- Find reviews about Kindle
SELECT * FROM mindsdb.reviews_kb
WHERE content LIKE 'what are the best kindle reviews'
LIMIT 10;

Via Python SDK

First, install the MindsDB SDK:

pip install mindsdb_sdk

Then use this code to query your knowledge base:

import mindsdb_sdk

# Connect to MindsDB server
server = mindsdb_sdk.connect('http://127.0.0.1:47334')

# Access your knowledge base
reviews_kb = server.knowledge_bases.get('mindsdb.reviews_kb')

# Search for content
df = reviews_kb.find('what are the best kindle reviews').fetch()

Advanced Customization

For those who want deeper customization, MindsDB offers:

• Custom embedding model selection
• Vector database configurations
• Various chunking strategies

However, the default settings work excellently for most use cases without requiring manual configuration.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.