Jenkins MCP server

The Jenkins Server MCP provides a standardized interface for AI assistants to interact with Jenkins CI/CD servers. Through this protocol, you can check build statuses, trigger builds, and retrieve build logs from Jenkins using a simple API.

Installation

To set up the Jenkins Server MCP:

1. Clone the repository:

   git clone https://github.com/yourusername/jenkins-server-mcp.git
   cd jenkins-server-mcp
   

2. Install dependencies:

   npm install
   

3. Build the project:

   npm run build
   

Configuration

The server requires specific environment variables to connect to your Jenkins server:

• JENKINS_URL: Your Jenkins server URL (defaults to 'http://sohoci.rd.tp-link.net/jenkins')
• JENKINS_USER: Jenkins username for authentication
• JENKINS_TOKEN: Jenkins API token for authentication

Claude Desktop Configuration

Configure the MCP server in your Claude Desktop settings file:

MacOS:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows:

%APPDATA%/Claude/claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "jenkins-server": {
      "command": "node",
      "args": ["/path/to/jenkins-server-mcp/build/index.js"],
      "env": {
        "JENKINS_URL": "https://your-jenkins-server.com",
        "JENKINS_USER": "your-username",
        "JENKINS_TOKEN": "your-api-token"
      }
    }
  }
}

Available Tools

Get Build Status

Retrieve the status of a Jenkins build:

const result = await mcpClient.useTool("jenkins-server", "get_build_status", {
  jobPath: "view/xxx_debug",
  buildNumber: "lastBuild"  // Optional, defaults to lastBuild
});

Input Schema:

{
  "jobPath": "string",  // Path to Jenkins job
  "buildNumber": "string"  // Optional, build number or "lastBuild"
}

Trigger Build

Start a new Jenkins build with custom parameters:

const result = await mcpClient.useTool("jenkins-server", "trigger_build", {
  jobPath: "view/xxx_debug",
  parameters: {
    BRANCH: "main",
    BUILD_TYPE: "debug"
  }
});

Input Schema:

{
  "jobPath": "string",  // Path to Jenkins job
  "parameters": {
    // Build parameters as key-value pairs
  }
}

Get Build Log

Retrieve the console output from a Jenkins build:

const result = await mcpClient.useTool("jenkins-server", "get_build_log", {
  jobPath: "view/xxx_debug",
  buildNumber: "lastBuild"
});

Input Schema:

{
  "jobPath": "string",  // Path to Jenkins job
  "buildNumber": "string"  // Build number or "lastBuild"
}

Usage Examples

Checking the Latest Build Status

// Check status of the latest build in a job
const status = await mcpClient.useTool("jenkins-server", "get_build_status", {
  jobPath: "my-project/main-pipeline"
});

console.log(`Build status: ${status.result}`);
console.log(`Started at: ${status.timestamp}`);

Triggering a Parameterized Build

// Trigger a new build with custom parameters
const triggerResult = await mcpClient.useTool("jenkins-server", "trigger_build", {
  jobPath: "my-project/release-build",
  parameters: {
    BRANCH: "release/v2.0",
    ENVIRONMENT: "staging",
    RUN_TESTS: true
  }
});

console.log(`Build queued: ${triggerResult.queuedItemUrl}`);

Retrieving and Analyzing Build Logs

// Get build log for debugging failures
const logs = await mcpClient.useTool("jenkins-server", "get_build_log", {
  jobPath: "my-project/nightly-build",
  buildNumber: "42"
});

// Check if logs contain error patterns
if (logs.includes("ERROR:") || logs.includes("BUILD FAILED")) {
  console.log("Build contains errors!");
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.