Use MCP servers with Pi without burning your context window.

Mario wrote about why you might not need MCP. The problem: tool definitions are verbose. A single MCP server can burn 10k+ tokens, and you're paying that cost whether you use those tools or not. Connect a few servers and you've burned half your context window before the conversation starts.

His take: skip MCP entirely, write simple CLI tools instead.

But the MCP ecosystem has useful stuff - databases, browsers, APIs. This adapter gives you access without the bloat. One proxy tool (~200 tokens) instead of hundreds. The agent discovers what it needs on-demand. Servers only start when you actually use them.

pi install npm:pi-mcp-adapter

Restart Pi after installation.

Create ~/.pi/agent/mcp.json:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"]
    }
  }
}

Servers are lazy by default — they won't connect until you actually call one of their tools. The adapter caches tool metadata so search and describe work without live connections.

mcp({ search: "screenshot" })

chrome_devtools_take_screenshot
  Take a screenshot of the page or element.

  Parameters:
    format (enum: "png", "jpeg", "webp") [default: "png"]
    fullPage (boolean) - Full page instead of viewport

mcp({ tool: "chrome_devtools_take_screenshot", args: '{"format": "png"}' })

Note: args is a JSON string, not an object.

Two calls instead of 26 tools cluttering the context.

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["-y", "some-mcp-server"],
      "lifecycle": "lazy",
      "idleTimeout": 10
    }
  }
}

• lazy (default) — Don't connect at startup. Connect on first tool call. Disconnect after idle timeout. Cached metadata keeps search/list working without connections.
• eager — Connect at startup but don't auto-reconnect if the connection drops. No idle timeout by default (set idleTimeout explicitly to enable).
• keep-alive — Connect at startup. Auto-reconnect via health checks. No idle timeout. Use for servers you always need available.

{
  "settings": {
    "toolPrefix": "server",
    "idleTimeout": 10
  },
  "mcpServers": { }
}

Per-server idleTimeout overrides the global setting.

By default, all MCP tools are accessed through the single mcp proxy tool. This keeps context small but means the LLM has to discover tools via search. If you want specific tools to show up directly in the agent's tool list — alongside read, bash, edit, etc. — add directTools to your config.

Per-server:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"],
      "directTools": true
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "directTools": ["search_repositories", "get_file_contents"]
    },
    "huge-server": {
      "command": "npx",
      "args": ["-y", "mega-mcp@latest"]
    }
  }
}

To set a global default for all servers:

{
  "settings": {
    "directTools": true
  },
  "mcpServers": {
    "huge-server": {
      "directTools": false
    }
  }
}

Per-server directTools overrides the global setting. The example above registers direct tools for every server except huge-server.

Each direct tool costs ~150-300 tokens in the system prompt (name + description + schema). Good for targeted sets of 5-20 tools. For servers with 75+ tools, stick with the proxy or pick specific tools with a string[].

Direct tools register from the metadata cache (~/.pi/agent/mcp-cache.json), so no server connections are needed at startup. On the first session after adding directTools to a new server, the cache won't exist yet — tools fall back to proxy-only and the cache populates in the background. Restart Pi and they'll be available. To force it: /mcp reconnect <server> then restart.

Interactive configuration: Run /mcp to open an interactive panel showing all servers with connection status, tools, and direct/proxy toggles. You can reconnect servers, initiate OAuth, and toggle tools between direct and proxy — all from one overlay. Changes are written to your config file; restart Pi to apply.

Subagent integration: If you use the subagent extension, agents can request direct MCP tools in their frontmatter with mcp:server-name syntax. See the subagent README for details.

Already have MCP set up elsewhere? Import it:

{
  "imports": ["cursor", "claude-code", "claude-desktop"],
  "mcpServers": { }
}

Supported: cursor, claude-code, claude-desktop, vscode, windsurf, codex

Add .pi/mcp.json in a project root for project-specific servers. Project config overrides global and imported servers.

Search includes both MCP tools and Pi tools (from extensions). Pi tools appear first with [pi tool] prefix. Space-separated words are OR'd.

Tool names are fuzzy-matched on hyphens and underscores — context7_resolve_library_id finds context7_resolve-library-id.

• One mcp tool in context (~200 tokens) instead of hundreds
• Servers are lazy by default — they connect on first tool call, not at startup
• Tool metadata is cached to disk so search/list/describe work without live connections
• Idle servers disconnect after 10 minutes (configurable), reconnect automatically on next use
• npx-based servers resolve to direct binary paths, skipping the ~143 MB npm parent process
• MCP server validates arguments, not the adapter
• Keep-alive servers get health checks and auto-reconnect
• Specific tools can be promoted from the proxy to first-class Pi tools via directTools config, so the LLM sees them directly instead of having to search

• OAuth tokens obtained externally (no browser flow)
• No automatic token refresh
• Cross-session server sharing not yet implemented (each Pi session runs its own server processes)