🔌 Pi MCP Client

Connect Pi to MCP servers so the model can use their tools and read their resources. You can also browse, preview, and use server-provided prompts.

🚀 Installation

pi install npm:pi-mcp-client

✨ Usage

Start a new Pi session, then add Cloudflare's public documentation server:

/mcp add --scope global cloudflare-docs https://docs.mcp.cloudflare.com/mcp

This server doesn't require credentials. Ask Pi:

Search Cloudflare's documentation for how to deploy a Worker.

You configure servers and sign in when needed. The model finds and uses relevant tools and resources—you don't need to select tools before asking a question. When a server needs more information during a tool call, Pi asks you directly and sends only what you submit. See server requests for input.

Use these commands in Pi to manage your connections:

Command	Purpose
/mcp	Check connection status, available-tool counts, and tools loaded for the model when troubleshooting or checking your setup.
/mcp login <server>	Sign in to an HTTP server. Only this command opens the login browser.
/mcp prompt <server> [name] [argument=value ...]	Browse prompts or open one by name, then review a preview before using it.
/mcp reload	Apply changes after editing your MCP configuration files.

Only configure servers you trust: local servers and secret commands run with your permissions. Tool activation isn't a per-call approval prompt. See trust and permissions.

⚙️ Configuration

Store server definitions in ~/.pi/agent/mcp.json or a trusted project's .mcp.json. Project servers load only after an explicit trust decision. Project definitions replace same-named global definitions in full. You can edit these files or use /mcp add and /mcp remove. To reuse a Claude/Cursor JSON or Codex TOML file, run /mcp import --scope global <path> and review the selected connections before saving.

Detailed guides:

• Configuration: HTTP and stdio servers, environment variables, secret commands, tool filters, and timeouts.
• Authentication: OAuth setup, pre-registered clients, remote login, and logout.
• Commands: Server management, tool browsing, prompt selection, and resource watches. These are commands you run in Pi.
• Tool reference: Discovery, activation, resource reads, and argument completions. This is the model's interface, not a user API.
• Behavior: When servers connect, when tools become available, and what permissions they have.
• Troubleshooting: Error codes, recovery, and large results.

🧰 Requirements

• Pi 0.85.1 or later.
• Node.js 22 or later.
• The server executable for stdio connections.
• An available OS credential store for OAuth. Linux requires a working Secret Service/keyring session.

📄 License

MIT