Interact with your MLOps and LLMOps pipelines through your ZenML MCP server
Interact with your MLOps and LLMOps pipelines through your ZenML MCP server.
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.
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
stack_components_analysis — Analyze stack component usagerecent_runs_analysis — Analyze recent pipeline runsmost_recent_runs — Get N most recent runsget_run_template — Use get_snapshot insteadlist_run_templates — Use list_snapshots insteadCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| diagnose_zenml_setup | get_active_user and get_active_project |
| trigger_pipeline | get_step_logs, get_step_code, and get_deployment_logs |
| zenml_describe_resources | Discover supported resource types and bounded operation schemas |
| zenml_list_resources | List one resource type with validated filters and pagination |
| zenml_get_resource | Get one resource, with parent and project scope where required |
| zenml_create_resource | Create a supported resource from a typed payload |
| zenml_update_resource | Update one exact resource UUID |
| zenml_delete_resource | Delete or archive one exact resource UUID |
| zenml_action_resource | Run an allowlisted lifecycle or relation action without retries |
| Profile | Policy |
| compact | read_only |
| legacy | read_only |
{
"mcpServers": {
"zenml": {
"command": "/usr/local/bin/uv",
"args": [
"run",
"path/to/server/zenml_server.py"
],
"env": {
"LOGLEVEL": "WARNING",
"NO_COLOR": "1",
"ZENML_LOGGING_COLORS_DISABLED": "true",
"ZENML_LOGGING_VERBOSITY": "WARN",
"ZENML_ENABLE_RICH_TRACEBACK": "false",
"ZENML_MCP_PROFILE": "compact",
"ZENML_MCP_WRITE_POLICY": "read_write",
"PYTHONUNBUFFERED": "1",
"PYTHONIOENCODING": "UTF-8",
"ZENML_STORE_URL": "https://your-zenml-server-goes-here.com",
"ZENML_STORE_API_KEY": "YOUR_ZENML_STORE_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
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
| Variable | Description | Required |
|---|---|---|
| LOGLEVEL | Declared in the maintainer’s client configuration. | Check documentation |
| NO_COLOR | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_LOGGING_COLORS_DISABLED | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_LOGGING_VERBOSITY | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_ENABLE_RICH_TRACEBACK | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_MCP_PROFILE | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_MCP_WRITE_POLICY | Declared in the maintainer’s client configuration. | Check documentation |
| PYTHONUNBUFFERED | Declared in the maintainer’s client configuration. | Check documentation |
| PYTHONIOENCODING | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_STORE_URL | Declared in the maintainer’s client configuration. | Check documentation |
| ZENML_STORE_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Simple MCP Server w/ Shell Exec. Connect to Local via Ngrok, or Host Ubuntu24 Container via Docker
The local MCP server of ohmyho.st, hosting that a coding agent operates. It runs over stdio next to Codex, Claude Code, Cursor, Hermes or OpenClaw and lets the agent deploy the user's GitHub apps…
A Model Context Protocol (MCP) server that provides tools for querying Azure retail pricing information using the Azure Retail Prices API.
The official Python library for the cloudflare API