convez.ai
MCP ServerDevOps & InfraestruturaAvançado
Knuckles-Team

Systems Manager MCP

Knuckles-Team/systems-manager

Gerenciador de sistema agentic com MCP, multi-host e segurança enterprise

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que permite a agentes de IA gerenciar atualizações de sistema e instalação/upgrade de aplicações remotamente. Suporta orquestração multi-host via SSH com zero dependências remotas, integração com Pydantic AI agents, telemetria OpenTelemetry nativa e controle de acesso com políticas Eunomia.

Instalação

$npx convez-ai Knuckles-Team/systems-manager

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
3
Forks
1
Acompanhando
1
Saúde
37%
Último commit
há 2 dias
Versão
v2.2.11
Issues abertas
0
Contribuidores
4

Casos de uso

  • Automação de atualizações de sistema em múltiplos servidores via IA
  • Instalação e upgrade de aplicações remotas controladas por agents
  • Monitoramento e telemetria de hardware/SO integrado com LLMs
  • Orquestração zero-script de infraestrutura com controle centralizado

Veredito

Ferramenta sólida e production-ready para quem precisa de automação de infraestrutura agentic com segurança enterprise. Exige conhecimento de DevOps/SRE e é mais indicada para ambientes multi-servidor complexos do que para casos simples.

README

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

Systems Manager

CLI or API | MCP | Agent

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 1.32.0

Documentation — Installation, deployment, and usage across the CLI, API, MCP, and agent interfaces are maintained in the official documentation.


Overview

Systems Manager is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Systems Manager will update your system and install/upgrade applications. Additionally, as allow AI to perform these activities as an MCP Server.


Key Features

  • Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
  • Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
  • Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
  • Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

Multi-Host & Zero-Script Remote Orchestration

systems-manager supports full zero-script remote server telemetry and control plane routing out of the box.

  • Unified Inventory: Single source of truth inventory loaded dynamically from standard XDG paths (~/.config/agent_utilities/inventory.yaml).
  • Zero Remote Dependencies: Remote targets require only standard SSH access and a standard Python interpreter—no remote daemons, systemd configurations, or software packages are deployed on the target hosts.
  • Dynamic Telemetry Serialization (remote_eval): Telemetries (such as get_os_statistics(), get_hardware_statistics(), and process monitoring) are automatically packed and evaluated dynamically over secure SSH tunnels.

To configure and utilize the multi-host remote routing, see the detailed Multi-Host Architecture Guide.


CLI or API

This agent wraps the Systems Manager will update your system and install/upgrade applications. Additionally, as allow AI to perform these activities as an MCP Server API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.


MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool ModuleToggle Env VarEnabled by DefaultDescription & Nested Methods
MiscMISCTOOLTrueManage misc operations.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

  • CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
  • Environment Variables: Define standard environment variables:
    • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
    • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
  • HTTP SSE Request Headers: Pass custom headers during transport initialization:
    • x-mcp-enabled-tools / x-mcp-disabled-tools
    • x-mcp-enabled-tags / x-mcp-disabled-tags
  • HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
    • ?tools=tool1,tool2
    • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.


MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "systems-manager": {
      "command": "uvx",
      "args": [
        "--from",
        "systems-manager",
        "systems-manager-mcp"
      ],
      "env": {
        "SYSTEMS_API_KEY": "your_systems_api_key_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "systems-manager": {
      "command": "uvx",
      "args": [
        "--from",
        "systems-manager",
        "systems-manager-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "SYSTEMS_API_KEY": "your_systems_api_key_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "systems-manager": {
      "url": "http://localhost:8000/systems-manager/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name systems-manager-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e SYSTEMS_API_KEY="your_value" \
  knucklessg1/systems-manager:latest

Additional Deployment Options

systems-manager can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

  • Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
  • Remote URL — connect to a server deployed behind Caddy at http://systems-manager-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export SYSTEMS_API_KEY="your_value"

# Run the agent server
systems-manager-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  systems-manager-mcp:
    image: knucklessg1/systems-manager:latest
    container_name: systems-manager-mcp
    hostname: systems-manager-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  systems-manager-agent:
    image: knucklessg1/systems-manager:latest
    container_name: systems-manager-agent
    hostname: systems-manager-agent
    restart: always
    depends_on:
      - systems-manager-mcp
    env_file:
      - ../.env
    command: [ "systems-manager-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9009
      - MCP_URL=http://systems-manager-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9009:9009"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9009/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.


Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

  • Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
  • OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
  • Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

FeatureFunctionalityEnablement
Tool GuardSensitivity inspection with human-in-the-loop validationEnabled by default
Prompt Injection DefenseInput scanning, repetition monitoring, and recursive loop blocksEnabled by default
Context Safety GuardStuck-loop detectors and contextual overflow preemptive alertsEnabled by default

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install systems-manager[all]

# Using standard pip
python -m pip install systems-manager[all]

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

PageContents
Installationpip, source, extras, prebuilt Docker image
Deploymentrun the MCP and agent servers, Compose, Caddy + Technitium, env config
Usagethe MCP tools, the SystemsManager API, the CLI
Overviewecosystem role and concept map
Sudo Securityleast-privilege elevated-execution model
Multi-Hostzero-script remote telemetry and control plane
Day 0 Installationbare-metal to managed cluster node

AGENTS.md is the canonical contributor/agent guidance.


Repository Owners

GitHub followers GitHub User's stars


Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

  • Format code using ruff format .
  • Lint code using ruff check .
  • Validate type-safety with mypy .
  • Execute test suites using pytest
Ver o original no GitHub

Bom para

Relacionados