convez.ai
MCP ServerIntegração & APIsIntermediário
pc-software-org

AI Conductor - Agregador MCP Local

pc-software-org/ai-conductor

Proxy MCP que gerencia dinâmicamente servidores downstream em tempo real

Ver no GitHub
InicialPluginScore · de 0 a 100

Proxy MCP local que agrega múltiplos servidores MCP gerenciados dinamicamente em tempo de execução, sem necessidade de reiniciar o cliente. Permite adicionar/remover servidores, descobrir servidores em registries e criar cadeias de ferramentas sem interrupção.

Instalação

$npx convez-ai pc-software-org/ai-conductor

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 3 dias
Versão
v0.2.0
Issues abertas
6
Contribuidores
3

Casos de uso

  • Agregar múltiplas ferramentas MCP sem reiniciar Claude Desktop
  • Gerenciar credenciais de servidores via keychain do SO
  • Descobrir e instalar servidores MCP de registries oficiais
  • Manter conexões lazy com fallback em cache de capabilities

Veredito

Solução sólida para quem trabalha com múltiplos MCP servers. O gerenciamento em runtime elimina fricção operacional, mas requer Node.js 20+ e familiaridade com ecossistema MCP para máximo proveito.

README

A tradução para o português deste README ainda está na fila.

ai-conductor

A local MCP proxy / aggregator. You register it once with an MCP client (e.g. Claude Desktop or Claude Code), and it sits in front of multiple, dynamically managed downstream MCP servers.

Published on npm as mcp-proxy-conductor.

Why

Individual MCP servers are fiddly to set up and force an agent restart on every change. ai-conductor decouples that: downstream servers are added/removed at runtime, without restarting the upstream client. New tools appear immediately via MCP listChanged notifications.

  Claude (MCP client)
        │  upstream: stdio
        ▼
  ┌─────────────────────────┐
  │      ai-conductor       │   MCP server upstream, MCP client downstream
  └─────────────────────────┘
        │  downstream: stdio | Streamable HTTP | SSE
        ▼
  Server A   Server B   Server C  …  (managed at runtime)

Features

  • Runtime management of downstream servers via built-in meta-tools — no client restart.
  • Downstream transports: stdio, Streamable HTTP, SSE.
  • Aggregates tools, resources, and prompts from all downstreams, with per-server namespacing (serverId__name) so names never collide.
  • Lazy connections: downstreams connect on first use and disconnect after an idle timeout; capabilities are served from a cache so tools are advertised without connecting.
  • Credentials in the OS keychain — referenced from config, never stored in plaintext.
  • Persistence — added servers are stored and reconnected (lazily) on the next start.

Requirements

  • Node.js ≥ 20

Install & register

Register ai-conductor with your MCP client. With the Claude Code CLI:

claude mcp add conductor -s user -- npx -y mcp-proxy-conductor

Or add it manually to your client's MCP config:

{
  "mcpServers": {
    "conductor": { "command": "npx", "args": ["-y", "mcp-proxy-conductor"] }
  }
}

Restart the client once. ai-conductor then exposes its meta-tools.

Managing downstream servers

Manage downstreams conversationally through the meta-tools:

  • add_server — add and connect a downstream server at runtime (persists).
    • id: unique, alphanumeric/hyphen, no underscores.
    • transport: one of
      • { "type": "stdio", "command": "...", "args": [...], "env": { ... } }
      • { "type": "http", "url": "https://…/mcp", "headers": { ... } }
      • { "type": "sse", "url": "https://…/sse", "headers": { ... } }
  • remove_server — disconnect and remove a downstream server (persists). Arg: id.
  • list_servers — list managed servers with connection state (idle/connected/ error), whether capabilities come from cache, and capability counts.

Example

{
  "id": "filesystem",
  "transport": {
    "type": "stdio",
    "command": "npx",
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/some/dir"]
  }
}

Its tools then appear as filesystem__<toolname>, callable immediately — no restart.

Discovering servers from registries

Instead of typing transport details by hand, discover servers from MCP registries and install them through meta-tools:

  • list_registries — enumerate available registries with capability flags (canConnect, canDetectSecrets).
  • search_registry(query, sources?) — search for servers. Defaults to the official registry (registry.modelcontextprotocol.io); pass sources (ids from list_registries) to widen the search.
  • install_from_registry(ref, { id?, env?, secretBindings? }) — install a result by its ref. For entries that need secrets, store them with secret set and pass secretBindings: { ENV_NAME: "<keychain-name>" }; for required non-secret env, pass env: { ENV_NAME: "<value>" }.

Example: search, then install a server that needs a secret:

search_registry { "query": "filesystem" }
→ official:com.example/fs  (connectable, requiredSecrets: ["API_TOKEN"])

mcp-proxy-conductor secret set fs-token        # in your terminal
install_from_registry { "ref": "official:com.example/fs", "secretBindings": { "API_TOKEN": "fs-token" } }

Sources & capability asymmetry: the official registry provides structured run details and secret flags, so auto-connect and secret detection work fully. Glama is a discovery source (it lists servers but not a runnable command, so its entries are not auto-connectable — use the results to then add_server manually). Per-source failures are reported in the search result, never crashing the search.

Credentials

Secrets live in the OS keychain (macOS Keychain, Windows Credential Manager, Linux Secret Service) — never in config.json and never passed through the chat.

1. Store a secret with the CLI (the value is read from hidden stdin, not the chat):

mcp-proxy-conductor secret set my-token
# or pipe it (e.g. in scripts):
printf '%s' "$MY_TOKEN" | mcp-proxy-conductor secret set my-token

# remove it again:
mcp-proxy-conductor secret rm my-token

2. Reference it in add_server via ${keychain:<name>}:

{
  "id": "uptime",
  "transport": {
    "type": "http",
    "url": "https://example.com/mcp",
    "headers": { "Authorization": "Bearer ${keychain:my-token}" }
  }
}

References are resolved at connect time. Supported placeholder schemes (usable in any env or headers value, and combinable within a string):

ReferenceResolves from
${keychain:NAME}OS keychain (service mcp-proxy-conductor)
${env:VAR}process environment
${VAR}process environment (shorthand)

Headless Linux without a running Secret Service daemon cannot use the keychain — use ${env:…} there instead. A missing or unreachable secret surfaces as an error state for that one downstream (visible in list_servers); other servers keep working.

Lazy connections

To scale to many downstreams, connections are late-bound: at startup nothing is connected — tools/resources/prompts are advertised from a persisted capability cache. A downstream connects on the first actual call and is evicted after an idle timeout (default 5 minutes, override with CONDUCTOR_IDLE_TIMEOUT_MS, in ms; 0 disables eviction). The first call to an idle server therefore pays a one-time connect latency.

Development

pnpm install
pnpm test        # vitest
pnpm typecheck
pnpm build       # tsup → dist/index.js

Status & limitations

Local, single-user focus. Known limitations:

  • No automatic reconnect/backoff for a downstream that crashes (it returns to idle and reconnects on the next call).
  • Change notifications are coarse (all listChanged types emitted on any change).
  • HTTP downstreams do not auto-fall back to SSE; the transport type is explicit.

Planned, not yet implemented: multi-tenant/SaaS mode.

License

MIT © Patrick Cornelißen

Ver o original no GitHub

Bom para

Relacionados