Jenkins MCP Server

Jenkins MCP Server

Enables AI coding tools to interact with Jenkins CI instances behind Cloudflare Access, supporting job inspection, build logs, test results, and artifact retrieval.

Category
访问服务器

README

Jenkins MCP Server

An MCP (Model Context Protocol) server for interacting with Jenkins instances protected by Cloudflare Access. Built for use with Kiro and other MCP-compatible AI coding tools.

Prerequisites

  • Node.js (v18+)
  • cloudflared CLI installed
  • A Jenkins API token (generate one from Jenkins → Your User → Configure → API Token)

Installation

  1. Clone this repo:
git clone https://github.com/kmlarso6/jenkins-mcp-server.git
cd jenkins-mcp-server
  1. Install dependencies:
npm install

MCP Configuration

Add the following to your Kiro MCP config at ~/.kiro/settings/mcp.json (or your workspace .kiro/settings/mcp.json):

{
  "mcpServers": {
    "Jenkins": {
      "command": "node",
      "args": ["/path/to/jenkins-mcp-server/index.mjs"],
      "env": {
        "JENKINS_URL": "https://jenkins.devops.asu.edu",
        "JENKINS_USER": "{YOUR_EXCEPTION_ASURITE}",
        "JENKINS_TOKEN": "{YOUR_API_KEY}"
      },
      "disabled": false,
      "autoApprove": [
        "get_build",
        "get_build_log",
        "get_job",
        "list_builds",
        "get_test_results",
        "get_artifact",
        "download_test_results",
        "list_stages",
        "get_stage_log",
        "get_failed_tests",
        "compare_builds"
      ]
    }
  }
}

Replace:

  • /path/to/jenkins-mcp-server/index.mjs with the absolute path to your cloned copy
  • {YOUR_EXCEPTION_ASURITE} with your Jenkins username (exception ASURITE)
  • {YOUR_API_KEY} with your Jenkins API token

Cloudflare Access Authentication

The Jenkins instance is behind Cloudflare Access. Before using the MCP tools, you need a valid Cloudflare token.

Initial Login

cloudflared access login "https://jenkins.devops.asu.edu"

This prints an authorization URL. Open it in your browser, complete ASU SSO login, and the token is cached automatically at ~/.cloudflared/.

Token Verification

cloudflared access token -app=https://jenkins.devops.asu.edu

If this returns a JWT string, you're authenticated.

Token Expiry

Tokens expire after several hours. If MCP tool calls start failing with Cloudflare errors, re-run the login command above.

Installing the Kiro Skill

This repo includes a Kiro skill that helps the AI agent manage the Cloudflare auth flow automatically.

To install it, copy the skill into your Kiro skills directory:

cp -r skills/jenkins-access ~/.kiro/skills/

Once installed, Kiro will activate the skill when Jenkins access is needed or when auth errors occur.

Available Tools

Tool Description
get_build Get info about a specific build
get_build_log Get console output for a build
get_job Get job info and recent builds list
list_builds List recent builds with results
get_test_results Get test report for a build
get_artifact Read a text artifact inline
download_test_results Download Playwright artifacts to a local temp dir
list_stages List pipeline stages with status and duration
get_stage_log Get console log for a specific pipeline stage
get_failed_tests Get only failing test cases with error messages
compare_builds Compare test results between two builds

Job Path Format

Jenkins job paths follow the pattern: <GitHub-Org>/<repo-name>/<branch>

For example: MyOrg/my-repo/main

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