mcp -plugin
MCP server from jenkinsci/mcp-server-plugin
claude mcp add --transport stdio jenkinsci-mcp-server-plugin java -jar jenkins-mcp-server.jar \ --env JENKINS_HOME="Path to the Jenkins home directory" \ --env MCP_LOG_LEVEL="Optional: set log level (e.g., INFO, DEBUG)"
How to use
This MCP server provides a server-side implementation of the Model Context Protocol for Jenkins. It exposes Jenkins actions, jobs, and build information as MCP tools and resources so that clients such as large language models, IDEs, or automation agents can contextually query Jenkins capabilities, orchestrate builds, inspect job configurations, and retrieve contextual data through MCP transports. The server is designed to integrate with standard MCP clients via the supported transports and endpoints, enabling streaming, stateless, and SSE-based communication depending on the deployment needs.
To use the server, start Jenkins with the MCP plugin installed and run the MCP server component (the plugin acts as the server). Clients can then connect through the three MCP transports: SSE (/mcp-server/sse), Streamable HTTP (/mcp-server/mcp), and Stateless HTTP (/mcp-server/stateless). Once connected, clients can discover available MCP tools (wrappers around Jenkins APIs), invoke operations (such as listing jobs, triggering builds, or querying build status), and receive structured responses suitable for LLM-based guidance or automation workflows. Authentication relies on the same Jenkins credentials, typically via API tokens used in HTTP headers.
The MCP tools exposed by the plugin include wrappers for Jenkins jobs, builds, and likely common admin/monitoring actions. These tools are presented in a way that abstracts Jenkins’ internal APIs into MCP-friendly operations, handling parameter parsing and formatting of results for easy consumption by MCP clients.
How to install
Prerequisites:
- Java 11+ installed on the host (or the runtime environment where the MCP server jar will run)
- Jenkins installed and running (version 2.533 or higher as per plugin requirements)
- Access to the Jenkins installation where you will add the MCP Server Plugin
Installation steps:
- Install Jenkins Plugin
- Open Jenkins UI
- Navigate to Manage Jenkins -> Manage Plugins
- Install the MCP Server Plugin (search for MCP Server Plugin or MCP Server) and restart Jenkins if prompted
- Prepare the MCP server artifact
- Ensure you have the MCP server jar (jenkins-mcp-server.jar) available on the host where you will run the MCP server
- Place the jar in a dedicated directory (e.g., /opt/mcp/jenkins-mcp-server.jar)
- Run the MCP server
- Ensure Java is available in your environment
- Start the MCP server using the command below (adjust the path as needed)
java -jar /opt/mcp/jenkins-mcp-server.jar
- Verify the server is up
- Check the console/logs for successful startup messages indicating the MCP server is listening on the configured endpoints
- You can test the endpoints using curl or your MCP client against the standard endpoints: /mcp-server/sse, /mcp-server/mcp, /mcp-server/stateless, or /mcp-server/message depending on your configuration.
- Configure MCP clients
- Use the provided examples in the README to connect your MCP clients to the Jenkins MCP server endpoints with appropriate authentication headers (Basic auth using an API token or Bearer token if supported).
Optional post-install steps:
- Tune system properties as described in the README (origin validation, endpoint enable/disable flags) by setting the corresponding JVM system properties or Jenkins startup parameters.
Additional notes
- The MCP server integrates tightly with Jenkins concepts like jobs and builds; available tools depend on the plugin implementation and may be extended via McpServerExtension.
- If you enable origin validation, ensure your MCP clients can supply the Origin header or adjust system properties to relax validation during development.
- For security, always protect Jenkins API tokens and use HTTPS in production. The MCP client config examples in the README show how to supply Basic Auth headers or Bearer tokens.
- If you experience transport-specific issues (SSE, streamable HTTP, or stateless HTTP), verify the corresponding endpoint is enabled in your environment and that firewalls or reverse proxies allow the required traffic.
- Logs are your friend: check Jenkins logs and the MCP server jar’s stdout/stderr for troubleshooting hints, especially around tool discovery and parameter parsing.
Related MCP Servers
ai-code-helper
2025 年 AI 编程助手实战项目(作者:程序员鱼皮),基于 Spring Boot 3.5 + Java 21 + LangChain4j + AI 构建智能编程学习与求职辅导机器人,覆盖 AI 大模型接入、LangChain4j 核心特性、流式对话、Prompt 工程、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、Web 爬虫、安全防护、Vue.js 前端开发、SSE 服务端推送等企业级 AI 应用开发技术。帮助开发者掌握 AI 时代必备技能,熟悉 LangChain 框架,提升编程学习效率和求职竞争力,成为企业需要的 AI 全栈开发人才。
sonarqube
SonarQube MCP Server
PIXRA
Pixelize the real world on-chain
mcp-mianshiya
基于 Spring AI 的面试鸭搜索题目的 MCP Server 服务,快速让 AI 搜索企业面试真题和答案
api2mcp4j
This is a revolutionary AI MCP plugin with excellent pluggable and encapsulated features. With just a few lines of configuration, it can easily integrate into your Spring boot web program and give it MCP capabilities,inheriting the powerful engineering capabilities of the Spring series framework
quarkus-workshop-langchain4j
Quarkus Langchain4J Workshop