Alimenter votre agent
La commande propre à l'éditeur. Ce n'est pas un endpoint PlugMCP.
Host a copy with our keys and logs.
npx -y [email protected]Claude Code n'a pas de lien d'installation pour une commande locale. Copiez la commande ci-dessous et exécutez-la dans un terminal.
claude mcp add pi-mcp-client -- npx -y pi-mcp-client@0.12.0À exécuter dans un terminal.
{ "mcpServers": { "pi-mcp-client": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
URL distante ou commande sur votre machine ? Ce qui distingue les deux installations
Exécuter sur PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LancerDe l'éditeur
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.
[!NOTE] On Pi 0.99.1 and later, this extension is no longer needed for basic MCP use: Pi has built-in support for server tools, resources, and OAuth. Keep this extension if you need OS-backed credential storage or the additional features below.
MCP tools for Pi, discovered on demand and called natively through the official SDK.
Comparison with Pi 1.0.0.
Both read the same mcp.json files, but OAuth credentials don't transfer between
implementations. See
switching to built-in MCP.
pi install npm:pi-mcp-client
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:
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.
Store server definitions in ~/.pi/agent/mcp.json or a trusted project's
.pi/mcp.json, the same files and shape as Pi's built-in MCP support. Project
servers load only in a project that Pi trusts.
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:
Custom hosts can use the experimental pi-mcp-client/durable adapter for
metadata discovery, native tool activation, resource reads, and template
completion. It shares configuration and the MCP credential store with this
extension. See the durable host contract for installation,
restart ordering, trust, and UI requirements.
MCP tools for Pi, discovered on demand and called natively through the official SDK.
{ "mcpServers": { "pi-mcp-client": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}Outils
Pas encore de liste d'outils. Les serveurs distants en obtiennent une après le premier contrôle d'état.
FAQ
Copiez sur cette page la configuration stdio pour Cursor, Claude Desktop, Claude Code ou VS Code. Elle utilise l'installation de l'éditeur, pas un proxy PlugMCP.
Aucune variable d'environnement requise n'est indiquée sur cette fiche.
Pi MCP Client s'exécute en local via stdio.
Dernière vérification : 2026-10-28. MCP tools for Pi, discovered on demand and called natively through the official SDK.