Jenkins MCP Server

Jenkins MCP Server

An MCP server for interacting with a Jenkins CI/CD server. Allows you to trigger jobs, check build statuses, and manage your Jenkins instance through MCP.

Category
访问服务器

README

Jenkins MCP Server.

An MCP server for interacting with a Jenkins CI/CD server. Allows you to trigger jobs, check build statuses, and manage your Jenkins instance through MCP.

Features

  • Job Management: Trigger, list, and get detailed information about Jenkins jobs.
  • Build Status: Check the status of specific builds and retrieve console logs.
  • Queue Management: View items currently in the build queue.
  • Server Information: Get basic information about the connected Jenkins server.
  • LLM Integration: Includes prompts and configurations for summarizing build logs (demonstration).
  • Transport Support: Supports both STDIO and Streamable HTTP transports.
  • Input Validation: Uses Pydantic for robust input validation and error handling.
  • Compatibility: Fully compatible with the MCP Gateway.

Prerequisites

  • Python 3.12+
  • A running Jenkins instance
  • uv for package management

Installation

  1. Clone the repository:

    git clone https://github.com/AshwiniGhuge3012/jenkins-mcp-server
    cd jenkins-mcp-server
    
  2. Create a virtual environment:

    uv venv
    
  3. Activate the virtual environment:

    source .venv/bin/activate
    
  4. Install dependencies:

    uv pip install -e .
    
  5. Create a .env file: Create a .env file in the project root and add your Jenkins credentials and URL.

    JENKINS_URL="http://your-jenkins-instance:8080"
    JENKINS_USER="your-username"
    JENKINS_API_TOKEN="your-api-token"
    MCP_PORT=8010
    

Usage

Running the Server

You can run the server in two modes:

1. STDIO Mode (for direct interaction)

python jenkins_mcp_server_enhanced.py

2. HTTP Mode (for use with MCP Gateway)

python jenkins_mcp_server_enhanced.py --transport streamable-http --port 8010

The port can be configured via the --port argument or the MCP_PORT environment variable.

Available Tools

Here is a list of the tools exposed by this MCP server:

trigger_job

  • Description: Triggers a Jenkins job with optional parameters.
  • Parameters:
    • job_name (string): The name of the Jenkins job.
    • params (object, optional): Job parameters as a JSON object. For multiselect parameters, pass an array of strings.
  • Returns: A confirmation message with the queue URL.

get_job_info

  • Description: Gets detailed information about a Jenkins job, including its parameters.
  • Parameters:
    • job_name (string): The name of the Jenkins job.
  • Returns: An object containing the job's description, parameters, and last build number.

get_build_status

  • Description: Gets the status of a specific build.
  • Parameters:
    • job_name (string): The name of the Jenkins job.
    • build_number (integer): The build number.
  • Returns: An object with the build status, timestamp, duration, and URL.

get_console_log

  • Description: Retrieves the console log for a specific build.
  • Parameters:
    • job_name (string): The name of the Jenkins job.
    • build_number (integer): The build number.
    • start (integer, optional): The starting byte position for fetching the log.
  • Returns: The console log text and information about whether more data is available.

list_jobs

  • Description: Lists all available jobs on the Jenkins server.
  • Parameters: None
  • Returns: A list of job names.

get_queue_info

  • Description: Gets information about builds currently in the queue.
  • Parameters: None
  • Returns: A list of items in the queue.

server_info

  • Description: Gets basic information about the Jenkins server.
  • Parameters: None
  • Returns: The Jenkins version and URL.

summarize_build_log

  • Description: (Demonstration) Summarizes a build log using a pre-configured LLM prompt.
  • Parameters:
    • job_name (string): The name of the Jenkins job.
    • build_number (integer): The build number.
  • Returns: A placeholder summary and the prompt that would be used.

Example Usage with mcp-cli

First, ensure the server is running in HTTP mode and registered with your MCP Gateway.

# Example: Triggering a job
mcp-cli cmd --server gateway --tool jenkins_server.trigger_job --tool-args '{"job_name": "my-test-job", "params": {"branch": "develop", "deploy": true}}'

# Example: Listing all jobs
mcp-cli cmd --server gateway --tool jenkins_server.list_jobs

Dependencies

  • fastmcp
  • pydantic
  • requests
  • python-dotenv

License

This project is licensed under the Apache 2.0 License.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选