RelevanceAI MCP server

Bridges Claude with RelevanceAI's API, enabling direct access to RelevanceAI tools within conversations through environment variable authentication and stdio transport.
Back to servers
Provider
RLeek
Release date
Mar 20, 2025
Language
TypeScript

This MCP Proxy server acts as a middleware that connects to the Relevance AI service, allowing you to integrate AI functionality with various applications. It simplifies the process of handling authentication and communication with the Relevance AI backend.

Setup Instructions

Follow these steps to get your MCP Proxy server up and running:

  1. Clone the repository to your local machine:

    git clone <repository-url>
    
  2. Install the required dependencies:

    npm i
    
  3. Create your environment configuration:

    cp .env.example .env
    
  4. Edit the .env file to add your Relevance authentication token and region settings.

  5. Copy the path to the run.sh file in the repository.

  6. Configure your MCP thing by pasting the path to the run.sh file, then click "Add" to complete the setup.

Usage

Once configured, your MCP Proxy will connect to the Relevance AI service and begin handling requests. The proxy allows you to query information (like searching for "oranges" in the example) and will return relevant results from the AI service.

Troubleshooting

If you encounter any issues with the proxy:

  • Check the logs.txt file which contains detailed logging information about the server's operation.
  • Verify that your authentication token and region settings in the .env file are correct.
  • Ensure that the path to the run.sh file was correctly added to your MCP thing configuration.

Limitations

Please note that this is a proof-of-concept implementation and may have various limitations in functionality and performance.

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.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later