https://github.com/npow/metaflow-mcp-server
MCP server for Metaflow -- give your AI coding agent superpowers over your ML workflows
https://github.com/npow/metaflow-mcp-server
ai-agents claude-code developer-tools llm-tools mcp mcp-server metaflow ml-workflows mlops model-context-protocol
Last synced: about 2 months ago
JSON representation
MCP server for Metaflow -- give your AI coding agent superpowers over your ML workflows
- Host: GitHub
- URL: https://github.com/npow/metaflow-mcp-server
- Owner: npow
- License: apache-2.0
- Created: 2026-02-20T06:14:34.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2026-02-20T06:55:47.000Z (4 months ago)
- Last Synced: 2026-02-20T10:24:34.326Z (4 months ago)
- Topics: ai-agents, claude-code, developer-tools, llm-tools, mcp, mcp-server, metaflow, ml-workflows, mlops, model-context-protocol
- Language: Python
- Size: 4.6 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-metaflow - metaflow-mcp-server - MCP server for inspecting runs, logs, and artifacts from any AI agent. (Developer Tooling)
README
# Metaflow MCP Server
[](https://github.com/npow/metaflow-mcp-server/actions/workflows/ci.yml)
[](https://pypi.org/project/metaflow-mcp-server/)
[](https://pypi.org/project/metaflow-mcp-server/)
[](LICENSE)
[](https://modelcontextprotocol.io/) [](https://mintlify.com/npow/metaflow-mcp-server)
Give your coding agent superpowers over your Metaflow workflows. Instead of writing throwaway scripts to check run status or dig through logs, just ask -- your agent will figure out the rest.
Works with any Metaflow backend: local, S3, Azure, GCS, or Netflix internal.
## Tools
| Tool | Description |
|------|-------------|
| `get_config` | What backend am I connected to? (also returns your default namespace) |
| `list_flows` | What flows exist in a namespace? |
| `search_runs` | Find recent runs of any flow |
| `get_run` | Step-by-step breakdown of a run |
| `get_task_logs` | Pull stdout/stderr from a task |
| `list_artifacts` | What did this step produce? |
| `get_artifact` | Grab an artifact's value |
| `get_latest_failure` | What broke and why? |
| `search_artifacts` | Which runs produced a named artifact? |
## Quickstart
```bash
pip install metaflow-mcp-server
claude mcp add --scope user metaflow -- metaflow-mcp-server
```
That's it. Restart Claude Code and start asking questions about your flows.
**To upgrade:**
```bash
pip install --upgrade metaflow-mcp-server
```
Then restart Claude Code (or reconnect via `/mcp`) to pick up the new version.
If Metaflow lives in a specific venv, point to it:
```bash
claude mcp add --scope user metaflow -- /path/to/venv/bin/metaflow-mcp-server
```
For other MCP clients, the server speaks stdio: `metaflow-mcp-server`
## How it works
Wraps the Metaflow client API. Whatever backend your Metaflow is pointed at, the server uses too -- no separate config needed. Sets `namespace(None)` at startup so production runs (Argo, Step Functions, Maestro) are visible alongside your dev runs.
Starts once per session, communicates over stdin/stdout. No daemon, no port.
## License
Apache-2.0