{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ss8qq34xq3xf","handle":"mltree-mcp","url":"https://wellknown.network/agents/mltree-mcp","links":{"self":"https://wellknown.network/agents/mltree-mcp/record.json","html":"https://wellknown.network/agents/mltree-mcp","markdown":"https://wellknown.network/agents/mltree-mcp/record.md","api":"https://wellknown.network/api/v1/agents/mltree-mcp","status":"https://wellknown.network/api/v1/agents/mltree-mcp/status","claim":"https://wellknown.network/agents/mltree-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mltree-mcp/claim.json","badge":"https://wellknown.network/agents/mltree-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mltree-mcp/history","tools":"https://wellknown.network/api/v1/agents/mltree-mcp/tools"},"ard":{"identifier":"urn:air::server:mltree-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mltree-mcp","summary":"An MCP server that maps your ML / GNN workflow as a node graph and records every experiment as a branching tree, while Codex or Claude Code works.","description":"# mltree-mcp\n\n[![test](https://github.com/yboulaamane/mltree-mcp/actions/workflows/test.yml/badge.svg)](https://github.com/yboulaamane/mltree-mcp/actions/workflows/test.yml)\n[![PyPI](https://img.shields.io/pypi/v/mltree-mcp)](https://pypi.org/project/mltree-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/mltree-mcp)](https://pypi.org/project/mltree-mcp/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-green)](https://github.com/yboulaamane/mltree-mcp/blob/main/LICENSE)\n\n**Your ML workflow as a node map, your experiments as a tree — filled in by your coding assistant as it works.**\n\n`mltree-mcp` is an [MCP](https://modelcontextprotocol.io) server for Codex, Claude Code and any other MCP client.\nWhile the assistant writes and runs your ML / QSAR / GNN code, it calls `mltree` tools to:\n\n- register each pipeline step (load → clean → featurize / graph-build → split → HPO → train → evaluate) as a **node**, with its own `.py` script, inputs, outputs and default params;\n- wire the steps into a **DAG**;\n- log every execution as a **run** with params, metrics and artifacts, branching from a parent run (HPO trials, GNN variants…), so experiments form a **mind-map tree** instead of being scattered down a notebook.\n\nEverything lives as plain files in your repo under `.mltree/`, and `mltree-mcp view` opens a KNIME-style map of it in your browser.\n\n![Demo: workflow map, experiment tree, compare, project switcher](https://raw.githubusercontent.com/yboulaamane/mltree-mcp/main/docs/demo.gif)\n\n![Workflow map](https://raw.githubusercontent.com/yboulaamane/mltree-mcp/main/docs/screenshot-map.png)\n\n![Experiment tree](https://raw.githubusercontent.com/yboulaamane/mltree-mcp/main/docs/screenshot-tree.png)\n\n> Status: **0.8.0**. MCP core, map viewer, `scan_project` for existing projects, shareable HTML export, running steps\n> and grid sweeps from the map (opt-in), data versions, compare with param changes / curves / code diffs, notes and\n> tags, GNN views, and now **PyPI p…","publisher":{"name":"Yassir Boulaamane","url":null},"homepage":"https://github.com/yboulaamane/mltree-mcp","repository":"https://github.com/yboulaamane/mltree-mcp#changelog","version":"0.8.0","license":null,"protocols":["mcp"],"tags":["claude-code","codex","experiment-tracking","gnn","graph-neural-networks","machine-learning","mcp","model-context-protocol","pipeline","pytorch-geometric","qsar"],"pricing":null,"endpoints":[{"url":"pypi:mltree-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":1,"provenance":"declared"},{"slug":"productivity.crm","name":"CRM & Sales","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":0.997,"provenance":"derived"}],"categories":["dev","knowledge","productivity"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mltree-mcp","registry":"pypi","observedAt":"2026-11-05T22:26:23.532Z","publishedAt":"2026-10-23T14:00:44.050775Z","latestVersion":"0.8.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mltree-mcp","url":"https://pypi.org/project/mltree-mcp/","firstSeenAt":"2026-10-24T17:28:26.463Z","fetchedAt":"2026-11-05T22:24:41.540Z","normalizedAt":"2026-11-05T22:24:41.540Z"}]},"firstSeenAt":"2026-10-24T17:28:26.463Z","updatedAt":"2026-11-05T22:26:23.532Z"}