convez.ai
MCP ServerIntegração & APIsIntermediário
Knuckles-Team

GitHub Agent MCP

Knuckles-Team/github-agent

MCP server para automação e integração completa com GitHub

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP de produção para integração com GitHub, oferecendo ferramentas otimizadas para gerenciar repositórios, issues e pull requests. Inclui agent integrado com suporte a telemetria nativa, segurança enterprise-grade e múltiplas interfaces (CLI, API, web).

Instalação

$npx convez-ai Knuckles-Team/github-agent

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 6 dias
Versão
v2.6.0
Issues abertas
0
Contribuidores
3

Casos de uso

  • Automação de fluxos de trabalho GitHub via Claude
  • Gerenciamento de repositórios, issues e PRs programaticamente
  • Integração de operações GitHub em agents de IA
  • Rastreamento e telemetria de operações GitHub com OpenTelemetry

Veredito

Ferramenta robusta e bem documentada para conectar GitHub com workflows de IA. A arquitetura action-routed reduz overhead de tokens e oferece suporte enterprise, mas exige familiaridade com MCP e configuração de credenciais GitHub.

README

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

Github Agent

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: 0.31.0

Documentation — Installation, deployment, and usage across the MCP, API, and CLI interfaces, including the integrated A2A agent server, are maintained in the official documentation.


Overview

Github Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with GitHub Agent for MCP.


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 GitHub Agent for MCP 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
RepoREPO_TOOLTrueManage GitHub repositories. Action-routed methods: create, delete, get, list, update.
IssueISSUE_TOOLTrueManage GitHub issues. Action-routed methods: create, get, list, update.
PullPULL_TOOLTrueManage GitHub pull requests. Action-routed methods: create, get, list, update.
ContentCONTENT_TOOLTrueManage GitHub contents. Action-routed methods: create, delete, get, update.
BranchBRANCH_TOOLTrueManage GitHub branches. Action-routed methods: create, delete, get, list.
CommitCOMMIT_TOOLTrueManage GitHub commits. Action-routed methods: get, list.
SearchSEARCH_TOOLTrueSearch GitHub repositories, issues, or code. Action-routed methods: code, issues, repositories.
OrgORG_TOOLTrueManage GitHub organizations. Action-routed methods: members, repos, teams.
CollaboratorCOLLABORATOR_TOOLTrueManage repository collaborators. Action-routed methods: add, list, remove.
ActionACTION_TOOLTrueManage GitHub actions workflows and runs. Action-routed methods: cancel, delete_run, get_run, list_runs, list_workflows, rerun, trigger_dispatch.
ReleaseRELEASE_TOOLTrueManage repository releases. Action-routed methods: create, delete, get, list, update.

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": {
    "github-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "github-agent",
        "github-mcp"
      ],
      "env": {
        "GITHUB_URL": "your_github_url_here",
        "GITHUB_VERIFY": "your_github_verify_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "GITHUB_TOKEN": "your_github_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": {
    "github-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "github-agent",
        "github-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "GITHUB_URL": "your_github_url_here",
        "GITHUB_VERIFY": "your_github_verify_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here",
        "GITHUB_TOKEN": "your_github_token_here"
      }
    }
  }
}

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

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

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name github-agent-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e GITHUB_URL="your_value" \
  -e GITHUB_VERIFY="your_value" \
  -e DEBUG="your_value" \
  -e PYTHONUNBUFFERED="your_value" \
  -e GITHUB_TOKEN="your_value" \
  knucklessg1/github-agent:latest

Additional Deployment Options

github-agent 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://github-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 GITHUB_URL="your_value"
export GITHUB_VERIFY="your_value"
export DEBUG="your_value"
export PYTHONUNBUFFERED="your_value"
export GITHUB_TOKEN="your_value"

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

  github-agent-agent:
    image: knucklessg1/github-agent:latest
    container_name: github-agent-agent
    hostname: github-agent-agent
    restart: always
    depends_on:
      - github-agent-mcp
    env_file:
      - ../.env
    command: [ "github-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9016
      - MCP_URL=http://github-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9016:9016"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9016/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 github-agent[all]

# Using standard pip
python -m pip install github-agent[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 Api client, the CLI
Overviewsupervisor architecture and specialized agents
Conceptsconcept registry (CONCEPT:GH-*)

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