ZenML MCP Server

If you want an AI assistant working directly with ZenML, the zenml mcp server is the bridge. Interact with your MLOps and LLMOps pipelines through your ZenML MCP server.

What ZenML does

This project implements a Model Context Protocol (MCP) server for interacting with the ZenML API.

The Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It acts like a "USB-C port for AI applications" - providing a standardized way to connect AI models to different data sources and tools.

Tools it exposes

Once connected, the assistant can call these 8 tools directly:

• stack_components_analysis — Analyze stack component usage
• recent_runs_analysis — Analyze recent pipeline runs
• most_recent_runs — Get N most recent runs
• get_run_template — Use get_snapshot instead
• list_run_templates — Use list_snapshots instead
• Models — The Models tool exposed by this server
• Diagnostics — The Diagnostics tool exposed by this server
• Prerequisites — You will need to have access to a deployed ZenML server. If you don't have one, you can sign up for a free trial at ZenML Pro and

Installing the zenml mcp server

The server is distributed via npm as cloudflared, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 8 environment variables: LOGLEVEL, NO_COLOR, ZENML_LOGGING_COLORS_DISABLED, ZENML_LOGGING_VERBOSITY, ZENML_ENABLE_RICH_TRACEBACK, PYTHONUNBUFFERED, PYTHONIOENCODING, ZENML_STORE_URL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

You will need to have access to a deployed ZenML server. If you don't have one, you can sign up for a free trial at ZenML Pro and we'll manage the deployment for you. > Tip: Once you have a ZenML server, check out the MCP Settings page in your dashboard for the easiest setup experience. > Compatibility: This MCP server is

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. ZenML sits in that group, and the shape of its toolset — stack_components_analysis, recent_runs_analysis, most_recent_runs among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
• It will not start until its required credentials are present, so set those before wondering why the tools never appear.
• With 8 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use ZenML.
• Written in Python.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the zenml mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.