convez.ai
MCP ServerIntegração & APIsAvançado
modus-agendi

Managed Agent Control MCP

modus-agendi/managed-agent-control-mcp

Controle remoto para Managed Agents da Anthropic via MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que funciona como controle remoto para Claude Managed Agents, permitindo iniciar, observar e interagir com agentes gerenciados pela Anthropic a partir de qualquer cliente MCP (Claude.ai, Claude Code, Cursor). Suporta múltiplas estratégias de autenticação e pode rodar em stdio, Docker ou AWS Lambda.

Instalação

$npx convez-ai modus-agendi/managed-agent-control-mcp

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
1
Forks
1
Acompanhando
0
Saúde
75%
Último commit
há 2 meses
Versão
—
Issues abertas
8
Contribuidores
2

Casos de uso

  • Gerenciar e orquestrar agentes Claude desde interfaces customizadas
  • Integrar Managed Agents em workflows de automação com outras ferramentas
  • Monitorar e interagir com agentes em tempo real de qualquer cliente MCP

Veredito

Ferramenta robusta e bem arquitetada para integração profissional com Managed Agents. Recomendada para times que precisam orquestrar agentes Claude em infraestrutura própria com autenticação enterprise-grade.

README

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

managed-agent-control-mcp

Start, observe, and interact with Claude Managed Agents from any MCP client (Claude.ai, Claude Code, Cursor, mcp-remote, your own agent, …).

CI PyPI Python License: MIT

Claude Managed Agents run on Anthropic's platform — each is an agent definition (model, system prompt, tools, skills) that executes inside a sandbox environment. This MCP server puts a remote control on those agents: connect it to any MCP client and you can launch an agent, watch what it does, reply to it, approve the tools it wants to run, and stop it. Claude.ai is the showcase client (do it all from a normal conversation), but the same tools work from Claude Code, Cursor, mcp-remote, the MCP Inspector, or a custom MCP client. It is the runtime companion to the Terraform provider that defines agents declaratively.

It runs as a local stdio server, a generic HTTP container, or on AWS Lambda, with pluggable inbound auth (static bearer, generic OIDC, or an AWS Cognito preset).

[!NOTE] This is a community project. It is not maintained by, endorsed by, or affiliated with Anthropic. The Managed Agents API is a beta API (managed-agents-2026-04-01).

How it works

MCP client ──MCP──▶ managed-agent-control-mcp ──HTTPS (x-api-key)──▶ Managed Agents API
(Claude.ai,         (this server: tools + auth)                     (agents run here)
 Claude Code, …)

You drive a loop: discover an agent → start a session → observe by polling events → interact (reply / interrupt / approve tools) → end. Because MCP tool calls are request/response, observation is by polling (session_events / session_get) — there is no live stream into the chat.

Quickstart (local, <2 min)

You need an ANTHROPIC_API_KEY with Managed Agents access and uv.

git clone https://github.com/modus-agendi/managed-agent-control-mcp
cd managed-agent-control-mcp
uv sync

# Run the server over stdio:
ANTHROPIC_API_KEY=sk-ant-... uv run python -m managed_agents_mcp

Explore the tools interactively with the MCP Inspector:

ANTHROPIC_API_KEY=sk-ant-... npx @modelcontextprotocol/inspector \
  uv run python -m managed_agents_mcp

Register it with Claude Code (a project-scoped .mcp.json is included):

claude mcp add managed-agent-control -- uv run python -m managed_agents_mcp

Once published to PyPI, you can skip the clone: uvx managed-agent-control-mcp.

Tools

TierToolDoes
Discoveragent_list / agent_getFind an agent and inspect its config
environment_list / environment_getFind a sandbox environment
vault_list / vault_getFind a credential vault to attach at session_start
memory_store_list / memory_store_getFind a persistent memory store
Startsession_startCreate a session and (optionally) send the first instruction
Observesession_getStatus (idle/running/…) + token usage
session_listList sessions
session_eventsPoll the agent's output/activity (cursor + type filter)
Interactsession_messageSend a message / continue a turn
session_interruptStop or redirect a running agent
session_respondApprove/deny a tool the agent is waiting on
Destructive 🔒session_archive / session_deleteArchive (keep history) or delete

See docs/tools.md for every argument and return shape.

Configuration

Only ANTHROPIC_API_KEY is required for local use. Full reference in docs/configuration.md.

Env varPurpose
ANTHROPIC_API_KEYRequired. Operator key the server acts with.
ANTHROPIC_BASE_URLOverride the API base URL (gateways/testing).
MCP_AUTH_MODEInbound auth for HTTP: bearer, oidc, cognito (comma-separated to combine).
MCP_BEARER_TOKENShared token for bearer mode.
MCP_OIDC_ISSUER / MCP_OIDC_JWKS_URL / MCP_OIDC_AUDIENCEJWT verification for oidc/cognito.
MCP_ALLOWLIST_AGENTS_ACTIVEtrue activates the agent allowlist (default off → all agents allowed).
MCP_ALLOWED_AGENT_IDSAgents session_start may launch when the allowlist is active.
MCP_ALLOW_DESTRUCTIVEfalse disables archive/delete.

Authentication

There are two auth layers (kept separate by design):

  • Outbound — how this server calls Anthropic: your ANTHROPIC_API_KEY.
  • Inbound — how MCP clients authenticate to this server. Pluggable and required for any HTTP deployment:
    • bearer — a shared static token. Simplest; works with Claude.ai connectors and mcp-remote.
    • oidc — verify JWTs from any OIDC provider (Auth0, Okta, Keycloak, Entra, Cognito).
    • cognito — the OIDC verifier plus the hosted-UI OAuth facade Cognito needs.

Setup and Claude.ai connector onboarding: docs/authentication.md.

[!WARNING] Never expose an HTTP deployment without an inbound auth mode set. Anyone who passes inbound auth can drive your Anthropic key — scope the key and use the guardrails.

Deployment

TargetHow
Local (stdio)uv run python -m managed_agents_mcp
Container (HTTP)docker build -f deploy/Dockerfile -t macmcp . && docker run -p 8000:8000 …
AWS LambdaSelf-contained Terraform module in deploy/aws-lambda/

Details: docs/deployment.md.

Documentation

  • Configuration — every env var + guardrails
  • Authentication — bearer / OIDC / Cognito + Claude.ai setup
  • Deployment — local, container, Lambda
  • Architecture — module map, the two auth layers, the polling model
  • Tools — full tool reference
  • Examples — end-to-end deployment walkthroughs (host + OAuth provider)

Contributing

Contributions welcome — see CONTRIBUTING.md and the Code of Conduct. Found a security issue? See SECURITY.md.

License

MIT — see LICENSE. Maintained by Andrei Svirida.

Ver o original no GitHub

Bom para

Relacionados