Bittensor MCP Server

The Bittensor MCP Server is a Model Context Protocol (MCP) implementation that enables AI assistants to interact with Bittensor's network of AI models. It serves as a bridge between AI assistants like Claude and Bittensor's various subnets, providing a standardized way to access and utilize Bittensor's capabilities.

Step 1: Get an API key

Go to the BitMind API Platform and create a new API key. Give it a name like "Bittensor MCP Server" and description such as "Personal access token for MCP server.". This will be used to authenticate requests from the MCP Server.

Step 2: Install the MCP Server

To use the Bittensor MCP Server with Claude or other MCP clients, you'll need to add it to your configuration file:

{
  "mcpServers": {
    "bittensor": {
      "command": "npx",
      "args": ["-y", "@bitmind/bittensor-mcp"],
      "env": {
        "BITMIND_API_TOKEN": "<YOUR_API_TOKEN>"
      }
    }
  }
}

Replace <YOUR_API_TOKEN> with your actual BitMind API token that we created in the previous step.

Next steps

Now you can access Bittensor subnet capabilities from your AI tool. Try asking the AI tool to interact with various subnets using natural language prompts.