home / mcp / jenkins mcp server

Jenkins MCP Server

jenkins-mcp-langchain

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "anil-appari007-jenkins-mcp-langchain": {
      "command": "jenkins-mcp-server",
      "args": [
        "--verbose"
      ],
      "env": {
        "JENKINS_URL": "http://your-jenkins-server:8080",
        "JENKINS_TOKEN": "YOUR_TOKEN",
        "JENKINS_PASSWORD": "your-password",
        "JENKINS_USERNAME": "your-username"
      }
    }
  }
}

You can run a Python-based Jenkins MCP Server that lets an AI assistant interact with Jenkins for insights, build management, and debugging. It follows the Model Context Protocol (MCP), enabling seamless collaboration between your Jenkins setup and AI tools.

How to use

You will connect an MCP-capable AI assistant to your Jenkins environment and use built-in tools to list jobs, trigger builds, inspect build details, and analyze logs. Use the MCP server with a compatible client or editor extension to issue high-level prompts like listing all jobs, getting job status, triggering builds, and fetching build logs. The server exposes resources and tools that let you inspect Jenkins state and orchestrate builds from natural language prompts.

How to install

Prerequisites: you need Python and network access to your Jenkins instance. You will install the MCP server package, then run the server locally.

# Option 1: Install as a Python package (recommended)
pip install jenkins-mcp-server==0.1.6

# Run the server (stdio mode)
jenkins-mcp-server --verbose

Or you can run it via a development path after cloning the project.

# Option 2: Clone and run
git clone https://github.com/yourusername/jenkins-mcp-server.git
cd jenkins-mcp-server

# Create a virtual environment and install dependencies
uv venv
uv pip install -e .

# Run the server (stdio mode)
python -m jenkins_mcp_server

Configuration and connection details

To connect your MCP client to Jenkins, you configure the MCP server that runs locally. You can run the server directly or configure it to be launched by your editor or tooling via stdio. The server supports verbose mode for troubleshooting.

# Run the MCP server with verbose logging
jenkins-mcp-server --verbose
```

```bash
# Or start via Python module (alternative startup)
python -m jenkins_mcp_server --verbose

Available tools

trigger-build

Triggers a Jenkins job build with optional parameters and returns queue information for the started build.

stop-build

Stops a running Jenkins build identified by job name and build number.

get-job-details

Fetches detailed information about a specific Jenkins job, including recent builds and configuration.

list-jobs

Lists all Jenkins jobs along with their current statuses.

get-build-info

Returns information about a specific build, including status, duration, and result.

get-build-console

Retrieves the console output from a specific build for debugging and analysis.

get-queue-info

Provides information about the Jenkins build queue, including pending builds.

get-node-info

Returns status and configuration details for a Jenkins node/agent.

list-nodes

Lists all Jenkins nodes/agents and their current statuses.

analyze-job-status

Analyzes all Jenkins jobs, identifies potential issues, and suggests improvements.

analyze-build-logs

Analyzes logs for a specific build to identify errors, warnings, and possible fixes.