MCP Jenkins Server

Provides secure, contextual AI access to Jenkins data and actions through MCP-compatible endpoints and tools.

python

76

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lanbaoshen-mcp-jenkins": {
      "command": "uvx",
      "args": [
        "mcp-jenkins",
        "--jenkins-url=xxx",
        "--jenkins-username=xxx",
        "--jenkins-password=xxx"
      ]
    }
  }
}

The Model Context Protocol (MCP) Jenkins integrates Jenkins with AI language models to enable secure, context-rich interactions while protecting data privacy. This MCP server lets you connect your Jenkins instance to AI copilots or agents, so you can query and act on Jenkins resources through a controlled, secure interface.

How to use

You will run the MCP server locally and connect your MCP client to it. The server exposes a set of endpoints and tools that let you retrieve Jenkins items, queue and build information, node configurations, and build outputs. Use your MCP client to instruct the AI to retrieve, inspect, or act on Jenkins data, and ensure you provide the Jenkins connection details the server expects.

How to install

Prerequisites you need before installing include Python and a compatible runtime tool for MCP servers.

# Install the MCP client runner (recommended)
pip install uv
uvx mcp-jenkins

# Or install the MCP server package directly
pip install mcp-jenkins
mcp-jenkins

# Optional: run via Docker
docker pull ghcr.io/lanbaoshen/mcp-jenkins:latest
docker run -p 9887:9887 --rm ghcr.io/lanbaoshen/mcp-jenkins:latest --transport streamable-http

Additional notes

Configuration snippets shown below illustrate how to run the MCP Jenkins server and how to connect MCP clients. The primary local runtime example uses a standard IO flow that launches the MCP server as a separate process and communicates over standard input/output.

Tools and endpoints

The MCP Jenkins server exposes a variety of capabilities to interact with Jenkins. You can retrieve information about items, nodes, queues, builds, and test reports, as well as control builds and manage queue items.

Available tools

get_item

Fetch a specific item by name from Jenkins.

get_item_config

Retrieve configuration details for a specific Jenkins item.

get_all_items

List all items present in the Jenkins instance.

query_items

Query items that match a given pattern.

build_item

Trigger or build a specified Jenkins item.

get_all_nodes

List all nodes configured in Jenkins.

get_node

Fetch details for a specific Jenkins node by name.

get_node_config

Retrieve the configuration for a particular Jenkins node.

get_all_queue_items

List all items currently in the Jenkins build queue.

get_queue_item

Fetch a specific queue item by its ID.

cancel_queue_item

Cancel a specific queue item by its ID.

get_build

Retrieve a specific build by job name and build number.

get_build_scripts

Get scripts associated with a specific build.

get_build_console_output

Fetch the console output for a specific build.

get_build_test_report

Retrieve the test report for a specific build.

get_running_builds

List all builds currently running in Jenkins.

stop_build

Stop a specific build by job name and build number.