knuckles-team/arr-mcp

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

6 stars 3 forks 质量 85 趋势 34MIT

Repository Install

Arr related MCP and A2A / AG-UI Agent

概览

— Installation, deployment, usage across the API, CLI, MCP, and maintained in the official documentation. is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Arr Suite MCP Server for Agentic AI!. - Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules. - Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking. - Out-of-the-box OpenTelemetry exports and native Langfuse tracing. This agent wraps the Arr Suite MCP Server for Agentic AI! API. The operator 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. This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

README

以下为原文 README 节选，完整内容请查看原文。

Arr Mcp

CLI or API | MCP

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

Overview
Key Features
Installation
CLI or API
MCP
- Dynamic Tool Selection & Visibility
Environment Variables
Security & Governance
Contribute

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: Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
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. The operator 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

在 GitHub 查看完整 README

安装

uvx --from arr-mcp[mcp

新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "arr-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "arr-mcp[mcp]",
        "arr-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "intent",
        "BAZARRTOOL": "True",
        "BAZARR_API_KEY": "your_bazarr_api_key_here",
        "BAZARR_BASE_URL": "http://localhost:6767",
        "CHAPTARRTOOL": "True",
        "CHAPTARR_BASE_URL": "http://localhost:8006",
        "CHAPTARR_TOKEN": "your_chaptarr_token_here",
        "LIDARRTOOL": "True",
        "LIDARR_BASE_URL": "http://localhost:8686",
        "LIDARR_TOKEN": "your_lidarr_token_here",
        "PROWLARRTOOL": "True",
        "PROWLARR_BASE_URL": "http://localhost:9696",
        "PROWLARR_TOKEN": "your_prowlarr_token_here",
        "RADARRTOOL": "True",
        "RADARR_BASE_URL": "http://localhost:7878",
        "RADARR_TOKEN": "your_radarr_token_here",
        "SEERRTOOL": "True",
        "SEERR_API_KEY": "your_seerr_api_key_here",
        "SEERR_BASE_URL": "http://localhost:5055",
        "SONARRTOOL": "True",
        "SONARR_BASE_URL": "http://localhost:8989",
        "SONARR_TOKEN": "your_sonarr_token_here"
      }
    }
  }
}