Supabase MCP server for AI agents

This open-source MCP (Model Context Protocol) server tracks premium global AI information, allowing you to easily access relevant AI updates in your daily LLM conversations without searching across multiple channels. It functions as a cloud-hostable or locally runnable service that interacts with LLMs through the MCP protocol, while its FastAPI backend periodically fetches and processes the latest AI information.

Installation

To set up the MCP server, follow these steps:

Prerequisites

Python 3.8 or higher
Supabase account for data storage
API access to desired AI information sources

Setting Up the Environment

Clone the repository:

git clone https://github.com/username/mcp-server.git
cd mcp-server

Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate

Install dependencies:
```
pip install -r requirements.txt
```
Configure environment variables:
```
cp .env.example .env
```
Edit the .env file to include your Supabase credentials and API keys.

Usage

Starting the MCP Server

To run the MCP server locally:

python main.py

For cloud deployment, the server can be containerized:

docker build -t mcp-server .
docker run -p 8000:8000 mcp-server

Configuring Information Sources

The MCP server comes pre-configured with various AI information sources, including:

X (Twitter) Accounts

Andrej Karpathy (@karpathy)
Ethan Mollick (@emollick)
Dan Shipper (@danshipper)
Gabriel (@GabrielPeterss4)
Justine Moore (@venturetwins)
Peter Yang (@peteryang)
Greg Isenberg (@gregisenberg)
Lenny Rachitsky (@lennysan)

Customizing Information Sources

To add custom information sources, modify the configuration file:

nano config/sources.json

Add your desired sources following this format:

{
  "twitter": [
    {"name": "New Account", "handle": "@newhandle"}
  ],
  "youtube": [
    {"name": "New Channel", "channel_id": "CHANNEL_ID"}
  ]
}

API Endpoints

The MCP server exposes several endpoints:

Query the latest AI information:

curl -X GET "http://localhost:8000/api/information?topic=generative_ai&limit=5"

Submit a specific information source for tracking:

curl -X POST "http://localhost:8000/api/sources" \
  -H "Content-Type: application/json" \
  -d '{"type": "twitter", "handle": "@newairesearcher"}'

Troubleshooting

Common Issues

Connection Problems: Ensure your Supabase credentials are correct in the .env file
Rate Limiting: If you encounter rate limiting from information sources, adjust the request frequency in the settings
Data Not Updating: Check the scheduler configuration to ensure periodic updates are running

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ai-surge-mcp" '{"command":"npx","args":["-y","ai-surge-mcp"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "ai-surge-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ai-surge-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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ai-surge-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ai-surge-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Supabase MCP server