Skip to main content
Glama
deenesjakoruzh
Hasinipachimatla

devagent

by Hasinipachimatla
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

多智能体开发自动化系统 — 智能体化 CI/CD 流水线

一个使用 FastAPI、Claude 驱动的智能体和模型上下文协议（MCP）的自动化智能体化 CI/CD 流水线，用于自动分析 GitHub 拉取请求、运行单元测试和检查文件。

项目架构

devagent/
├── agents/             # Claude-powered agents
│   ├── base_agent.py      # Base agent with tool execution loop
│   ├── reviewer_agent.py  # Reviewer agent parsing PR diffs
│   └── prompts.py         # System prompts
├── app/                # FastAPI application
│   ├── api/routes/        # API endpoints (health)
│   ├── services/          # Claude integration service
│   ├── config.py          # Settings and environment config
│   └── main.py            # FastAPI main entrypoint
├── mcp_server/         # MCP Server
│   ├── server.py          # MCPServer registration and endpoints
│   └── tools/             # MCP tools (fetch_pr_diff, lint, run_tests, search)
├── tests/              # Test suite (pytest)
│   ├── test_agents.py
│   ├── test_health.py
│   └── test_mcp_tools.py
├── .env.example        # Environment template
├── .gitignore          # Git ignore files
└── requirements.txt    # Python dependencies

Related MCP server: code-review-mcp-server

功能与 MCP 工具

  • BaseAgent：使用 Anthropic API（Claude 3.5 Sonnet）执行工具调用循环，以递归收集代码库信息。

  • ReviewerAgent：对 PR 差异执行代码审查，查找正确性缺陷、安全漏洞和代码质量问题。

  • MCP 工具：

    • fetch_pr_diff：获取 GitHub PR 的变更文件和补丁。

    • search_codebase：使用模式或文本搜索来搜索本地文件。

    • run_tests：在目标仓库中使用 pytest 运行单元测试。

    • lint_code：对目标文件运行 Ruff 检查器。

安装与设置

  1. 克隆仓库（推送到 GitHub 后）。

  2. 创建并激活虚拟环境：

    python -m venv .venv
# Windows:
.venv\Scripts\activate
# Linux/macOS:
source .venv/bin/activate

  3. 安装依赖：

    pip install -r requirements.txt

  4. 配置环境变量： 从模板创建 .env 文件并填写你的密钥：

    cp .env.example .env

    添加你的 ANTHROPIC_API_KEY，并可选择添加 GITHUB_TOKEN。

运行项目

运行 FastAPI 应用

uvicorn app.main:app --reload

在 http://localhost:8000/docs 访问 API 文档。

运行 MCP 服务器

要直接运行 MCP 服务器：

python mcp_server/server.py

运行测试

要运行所有测试并验证系统是否正常工作：

python -m pytest

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
Not graded
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • GitLab Review MCP

    lininn
    A
    license
    B
    quality
    C
    maintenance
    Enables code review operations on GitHub and GitLab, including fetching pull/merge requests, viewing diffs, adding comments, analyzing code quality, and creating merge requests directly from your MCP client.
    15
    34
    4
    MIT
  • Gitrama MCP Server by GitramaLLC

    Gitrama MCP Serverofficial

    GitramaLLC
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides 15 MCP tools for AI-powered Git intelligence, enabling commit messages, branch creation, PR descriptions, code review, diff analysis, and push operations directly from your AI assistant.
    MIT

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hasinipachimatla/devagent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server