convez.ai
MCP ServerAutomaçãoAvançado
Knuckles-Team

Arr MCP

Knuckles-Team/arr-mcp

MCP server para automação Arr Suite com agentes inteligentes e segurança enterprise

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP production-grade que integra a suite Arr para automação agentic AI com suporte a CLI, API e agentes inteligentes. Oferece ferramentas de ação otimizadas, segurança enterprise com policies Eunomia e OIDC, além de telemetria nativa com OpenTelemetry e Langfuse.

Instalação

$npx convez-ai Knuckles-Team/arr-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
6
Forks
3
Acompanhando
0
Saúde
37%
Último commit
há 6 dias
Versão
v3.1.1
Issues abertas
1
Contribuidores
4

Casos de uso

  • Automação de workflows com agentes IA usando Arr Suite
  • Integração agentic AI em aplicações enterprise com políticas de segurança
  • Orquestração de tarefas e ações via protocolo MCP com rastreamento distribuído

Veredito

Solução robusta e bem estruturada para integração com Arr Suite em contextos agentic. Requer familiaridade com MCP, segurança OIDC e arquitetura de agentes IA, sendo mais adequada para equipes enterprise.

README

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

Arr Mcp

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: 0.44.0

Documentation — Installation, deployment, usage across the API, CLI, MCP, and A2A agent interfaces, and guidance for provisioning the Arr Suite services are maintained in the official documentation.


Table of Contents


Overview

Arr Mcp is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Arr Suite MCP Server for Agentic AI!.


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.

CLI or API

This agent wraps the Arr Suite MCP Server for Agentic AI! 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

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

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": {
    "arr-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "arr-mcp",
        "arr-mcp"
      ],
      "env": {
        "ARR_HOST": "your_arr_host_here",
        "ARR_API_KEY": "your_arr_api_key_here",
        "PVR_API_KEY": "your_pvr_api_key_here",
        "PLEX_TOKEN": "your_plex_token_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": {
    "arr-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "arr-mcp",
        "arr-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "ARR_HOST": "your_arr_host_here",
        "ARR_API_KEY": "your_arr_api_key_here",
        "PVR_API_KEY": "your_pvr_api_key_here",
        "PLEX_TOKEN": "your_plex_token_here"
      }
    }
  }
}

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

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

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name arr-mcp-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e ARR_HOST="your_value" \
  -e ARR_API_KEY="your_value" \
  -e PVR_API_KEY="your_value" \
  -e PLEX_TOKEN="your_value" \
  knucklessg1/arr-mcp:latest

Additional Deployment Options

arr-mcp 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://arr-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 ARR_HOST="your_value"
export ARR_API_KEY="your_value"
export PVR_API_KEY="your_value"
export PLEX_TOKEN="your_value"

# Run the agent server
arr-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:
  arr-mcp-mcp:
    image: knucklessg1/arr-mcp:latest
    container_name: arr-mcp-mcp
    hostname: arr-mcp-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"

  arr-mcp-agent:
    image: knucklessg1/arr-mcp:latest
    container_name: arr-mcp-agent
    hostname: arr-mcp-agent
    restart: always
    depends_on:
      - arr-mcp-mcp
    env_file:
      - ../.env
    command: [ "arr-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9099
      - MCP_URL=http://arr-mcp-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9099:9099"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9099/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/index.md#a2a-agent.


Environment Variables

The Arr MCP and Agent servers support extensive environment configuration. The full list of supported variables is documented below:

VariableDescriptionDefaultRequired for
HOSTThe bind host for Streamable-HTTP or SSE transport.0.0.0.0Server Transport
PORTThe bind port for Streamable-HTTP or SSE transport.8000Server Transport
TRANSPORTMCP communication transport layer (stdio, streamable-http, sse).stdioServer Transport
ENABLE_OTELEnable OpenTelemetry logging and tracing integration.TrueObservability
EUNOMIA_TYPEAccess control policy engine type (none, embedded, remote).noneAccess Governance
EUNOMIA_POLICY_FILEScoped embedded policy file location.mcp_policies.jsonAccess Governance
DEFAULT_AGENT_NAMECustom name identification for the Graph Agent.Arr McpGraph Agent
ALLOWED_CLIENT_REDIRECT_URISPermitted client redirect URIs for authentication flows.NoneAuth Flow
AUTH_TYPEType of authentication used for A2A endpoints.NoneAuth Flow
SONARR_ENABLEDToggle to enable/disable Sonarr MCP tools and client.FalseSonarr Service
SONARR_BASE_URLBase API URL of your Sonarr service.NoneSonarr Service
SONARR_TOKENAuthentication API token for Sonarr.NoneSonarr Service
SONARR_SSL_VERIFYVerify SSL certificates for Sonarr requests.FalseSonarr Service
RADARR_ENABLEDToggle to enable/disable Radarr MCP tools and client.FalseRadarr Service
RADARR_BASE_URLBase API URL of your Radarr service.NoneRadarr Service
RADARR_TOKENAuthentication API token for Radarr.NoneRadarr Service
RADARR_SSL_VERIFYVerify SSL certificates for Radarr requests.FalseRadarr Service
LIDARR_ENABLEDToggle to enable/disable Lidarr MCP tools and client.FalseLidarr Service
LIDARR_BASE_URLBase API URL of your Lidarr service.NoneLidarr Service
LIDARR_TOKENAuthentication API token for Lidarr.NoneLidarr Service
LIDARR_SSL_VERIFYVerify SSL certificates for Lidarr requests.FalseLidarr Service
PROWLARR_ENABLEDToggle to enable/disable Prowlarr MCP tools and client.FalseProwlarr Service
PROWLARR_BASE_URLBase API URL of your Prowlarr service.NoneProwlarr Service
PROWLARR_TOKENAuthentication API token for Prowlarr.NoneProwlarr Service
PROWLARR_SSL_VERIFYVerify SSL certificates for Prowlarr requests.FalseProwlarr Service
BAZARR_ENABLEDToggle to enable/disable Bazarr MCP tools and client.FalseBazarr Service
BAZARR_BASE_URLBase API URL of your Bazarr service.NoneBazarr Service
BAZARR_API_KEYAuthentication API key for Bazarr.NoneBazarr Service
BAZARR_SSL_VERIFYVerify SSL certificates for Bazarr requests.FalseBazarr Service
SEERR_ENABLEDToggle to enable/disable Seerr MCP tools and client.FalseSeerr Service
SEERR_BASE_URLBase API URL of your Seerr service.NoneSeerr Service
SEERR_API_KEYAuthentication API key for Seerr.NoneSeerr Service
SEERR_SSL_VERIFYVerify SSL certificates for Seerr requests.FalseSeerr Service
CHAPTARR_ENABLEDToggle to enable/disable Chaptarr MCP tools and client.FalseChaptarr Service
CHAPTARR_BASE_URLBase API URL of your Chaptarr service.NoneChaptarr Service
CHAPTARR_TOKENAuthentication API token for Chaptarr.NoneChaptarr Service
CHAPTARR_SSL_VERIFYVerify SSL certificates for Chaptarr requests.FalseChaptarr Service

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 arr-mcp[all]

# Using standard pip
python -m pip install arr-mcp[all]

Usage & Quick Start

To launch and run arr-mcp services:

1. Launching the MCP Server

Launch the MCP server in standard I/O mode (ideal for IDEs):

arr-mcp

Or launch it as a Streamable-HTTP server on port 8000:

arr-mcp --transport streamable-http --port 8000

2. Running the Graph Agent Server

Start the interactive Pydantic AI Graph Agent CLI with OIDC token delegation and Eunomia policies:

arr-agent --provider openai --model-id gpt-4o

Repository Owners

GitHub followers GitHub User's stars


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 Python API clients, the CLI
Backing Platformprovision the Arr Suite services with Docker
Overviewecosystem role, enterprise readiness, configuration
Conceptsconcept registry (CONCEPT:ARR-*)

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