pi-mcp-adapter MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

One proxy tool (~200 tokens) instead of hundreds of tool schemas
On-demand tool discovery via search and describe verbs
Lazy / eager / keep-alive server lifecycle modes
Optional 'direct tools' promote hot tools to first-class Pi tools (~150-300 tokens each)
Bearer + OAuth (authorization code, client credentials) support

Demo ao vivo

Como fica na prática

pi-mcp-adapter.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pi-mcp-adapter": {
      "command": "npx",
      "args": [
        "-y",
        "pi-mcp-adapter"
      ],
      "_inferred": true
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "pi-mcp-adapter": {
      "command": "npx",
      "args": [
        "-y",
        "pi-mcp-adapter"
      ],
      "_inferred": true
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "pi-mcp-adapter": {
      "command": "npx",
      "args": [
        "-y",
        "pi-mcp-adapter"
      ],
      "_inferred": true
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pi-mcp-adapter": {
      "command": "npx",
      "args": [
        "-y",
        "pi-mcp-adapter"
      ],
      "_inferred": true
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "pi-mcp-adapter",
      "command": "npx",
      "args": [
        "-y",
        "pi-mcp-adapter"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

{
  "context_servers": {
    "pi-mcp-adapter": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "pi-mcp-adapter"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add pi-mcp-adapter -- npx -y pi-mcp-adapter

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: pi-mcp-adapter

Run Pi with 10+ MCP servers without blowing the context window

👤 Power users of the Pi coding agent ⏱ ~20 min intermediate

Quando usar: You want filesystem, git, github, postgres, playwright, fetch, firecrawl — more than Pi can eagerly load.

Pré-requisitos

Pi installed — See badlogic/pi-mono

Fluxo

Install the adapter

Run pi install npm:pi-mcp-adapter and restart Pi.✓ Copiado

→ Adapter listed in Pi's extensions
Configure all your MCPs

Add filesystem, git, github, postgres MCPs to pi-mcp-adapter in lazy mode.✓ Copiado

→ Servers registered; no boot overhead
Use via search

Use mcp({search: 'list files'}) to find the right tool, then call it.✓ Copiado

→ Relevant tool surfaced; then called

Resultado: Full MCP ecosystem available inside Pi, with a tiny context footprint.

Armadilhas

Search misses a tool because description is bad — Promote frequent tools to 'direct tools' so Pi sees them eagerly

Promote your 3 most-used MCP tools to first-class Pi tools

👤 Devs who use Pi daily ⏱ ~10 min beginner

Quando usar: You notice Pi calling mcp({search: ...}) every time before using filesystem read — add it as a direct tool to skip the dance.

Fluxo

Identify hot tools

Which mcp tool calls show up most in my recent Pi session logs?✓ Copiado

→ Top-N list
Mark as direct

Configure these as direct tools in pi-mcp-adapter settings.✓ Copiado

→ Tools now appear as first-class Pi tools

Resultado: Faster agent loop + lower token spend on repetitive tool discovery.

Armadilhas

Too many direct tools = defeats the purpose — Keep direct-tool count to ≤5; promote only if frequency is high

Use OAuth-protected MCP servers (e.g. Linear, Slack) with Pi

👤 Pi users on enterprise MCPs ⏱ ~15 min intermediate

Quando usar: Your MCP server requires OAuth and you'd rather not hand-craft token refresh.

Fluxo

Enable autoAuth

Set autoAuth: true in pi-mcp-adapter config for the linear server.✓ Copiado

→ Pi opens browser on first use
Authorize in browser

Approve the scope request; tokens are persisted.✓ Copiado

→ Subsequent calls use refreshed tokens automatically

Resultado: OAuth-protected MCP integrations 'just work' in Pi.

Armadilhas

Tokens stored unencrypted on disk — Use an encrypted home directory or OS keychain bridge

Combinações

Combine com outros MCPs para 10× de alavancagem

pi-mcp-adapter + filesystem + git-2 + github

Full dev loop inside Pi with lazy tool loading

Register filesystem, git, and github via pi-mcp-adapter in lazy mode.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
mcp	{search?: str} \| {describe?: str} \| {tool?: str, args?: JSON-string}	Universal proxy — the only tool Pi sees by default	~200 tokens eager + on-demand tool execution
/mcp-auth <server>	server name	Manually trigger OAuth for a specific server	free

Custo e limites

O que custa rodar

Cota de API: None of its own — proxies to underlying MCPs
Tokens por chamada: ~200 tokens eager overhead vs N*~500 for full tool listing
Monetário: Free, open source
Dica: Start lazy. Only promote tools to direct when telemetry shows Pi calls them ≥5× per session.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: OAuth tokens in ~/.pi/mcp-adapter/ — treat as sensitive

Saída de dados: Depends on configured upstream MCPs

Cross-session server sharing not implemented — each Pi session runs its own server processes (some memory cost).
Idle servers disconnect after 10 minutes by default — configurable via timeout setting.

Solução de problemas

Erros comuns e correções

mcp({tool: ...}) says 'tool not found'

Tool name is case-sensitive and namespaced by server. Use describe first to get the exact name.

OAuth loop never completes

Adapter's local callback port may be blocked. Check the redirect URL matches what's registered with the provider.

Server starts but tool calls hang

Upstream MCP crashed silently. Switch to eager mode temporarily to see the boot error.

Verificar: pi-mcp-adapter logs

Alternativas

pi-mcp-adapter vs. outros

Alternativa	Quando usar	Troca
Raw MCP integration	You run Pi with only 1-2 MCP servers	Simpler, but eats context as you add servers
mcp-gateway	You need security/PII redaction across many MCPs (not just token efficiency)	Python gateway; aimed at security more than token-saving

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills