This is an extension for the Pi Coding Agent (@mariozechner/pi-coding-agent) that integrates tools from a NanoClaw Model Context Protocol (MCP) server. It allows the Pi agent to dynamically fetch and execute tools exposed by a remote or local NanoClaw server.

How it works

When a new Pi session starts, the extension connects to the NanoClaw MCP server via a StreamableHTTPClientTransport. It authenticates using a Bearer token, queries the available tools (listTools), and automatically registers them within the Pi environment so the AI can use them.

Configuration

The extension is configured using the following environment variables:

NANOCLAW_MCP_TOKEN (Required): The authentication token for the MCP server. If missing, the extension will skip loading the tools.
NANOCLAW_MCP_URL (Optional): The URL of the NanoClaw MCP server endpoint. Defaults to http://localhost:3002/mcp.

Usage & Example

Ensure the extension is placed in your Pi extensions folder (or configured in your workspace to be loaded).
Set the necessary environment variables and start Pi:

export NANOCLAW_MCP_TOKEN="your-secret-token"
# Optional: export NANOCLAW_MCP_URL="http://localhost:3002/mcp"

pi

When Pi starts, you will see a notification in the UI: Connected to nanoclaw MCP server. Loaded X tools: tool_name, another_tool
You can now prompt the AI in the chat to use any of the dynamically loaded tools.

Connecting via SSH Tunnel

Often, the NanoClaw MCP server is running on a remote machine (e.g., a production server or a different development environment) and shouldn't be exposed directly to the public internet.

In this case, you can use an SSH Tunnel to securely forward the traffic.

Example: Forward remote port 3002 to your local port 3002:

ssh -L 3002:localhost:3002 user@remote-nanoclaw-host

Once the tunnel is active, you can simply run Pi locally without changing the NANOCLAW_MCP_URL (since it defaults to http://localhost:3002/mcp). The traffic will be securely routed through the SSH tunnel to the NanoClaw instance.