{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_j3xzq4yzn4fd","handle":"ml-inspector-mcp","url":"https://wellknown.network/agents/ml-inspector-mcp","links":{"self":"https://wellknown.network/agents/ml-inspector-mcp/record.json","html":"https://wellknown.network/agents/ml-inspector-mcp","markdown":"https://wellknown.network/agents/ml-inspector-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ml-inspector-mcp","status":"https://wellknown.network/api/v1/agents/ml-inspector-mcp/status","claim":"https://wellknown.network/agents/ml-inspector-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ml-inspector-mcp/claim.json","badge":"https://wellknown.network/agents/ml-inspector-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ml-inspector-mcp/history","tools":"https://wellknown.network/api/v1/agents/ml-inspector-mcp/tools"},"ard":{"identifier":"urn:air::server:ml-inspector-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ml-inspector-mcp","summary":"Framework-agnostic ML model analysis MCP server — evaluate, explain, and report on any trained model via Claude","description":"# ml-inspector-mcp\n\n[![PyPI](https://img.shields.io/pypi/v/ml-inspector-mcp)](https://pypi.org/project/ml-inspector-mcp/)\n[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\nFramework-agnostic ML model analysis MCP server. Drop in any trained model\nand test data — Claude evaluates it, explains predictions, detects drift,\nand generates PDF reports via natural language.\n\n## Installation\n\n```bash\npip install ml-inspector-mcp                                          # minimal\npip install \"ml-inspector-mcp[full]\"                                  # everything\npip install \"ml-inspector-mcp[sklearn-onnx,explain,reports]\"          # common combo\n```\n\n## Claude Desktop setup\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (Mac):\n\n```json\n{\n  \"mcpServers\": {\n    \"ml-inspector\": {\n      \"command\": \"ml-inspector\",\n      \"env\": {\n        \"ANTHROPIC_API_KEY\": \"your-key-here\",\n        \"MLFLOW_TRACKING_URI\": \"http://localhost:5000\"\n      }\n    }\n  }\n}\n```\n\n## Quick start\n\n```bash\npython examples/train_demo_model.py\n```\n\nThen in Claude Desktop:\n> \"Load the demo model from examples/demo_model.onnx\"\n> \"Load test data from examples/demo_test.csv\"\n> \"Evaluate the model and tell me how it's performing\"\n> \"Explain what drove the prediction for sample 5\"\n> \"Generate a PDF evaluation report\"\n\n## Model compatibility\n\n| Format | Framework | Install |\n|--------|-----------|---------|\n| `.onnx` | Any | Always works — recommended |\n| `.pkl` / `.joblib` | scikit-learn | `pip install \"ml-inspector-mcp[sklearn-onnx]\"` |\n| `.h5` / `.keras` | TensorFlow/Keras | `pip install \"ml-inspector-mcp[tensorflow]\"` |\n| `.pt` / `.pth` | PyTorch (full model only) | `pip install \"ml-inspector-mcp[pytorch]\"` |\n\n### Version mismatch fix\n\nIf you get version errors loading a `.pkl` or `.pt` file, export to ONNX first:\n\n```bash\n# scikit-learn — use the convert_to_onnx to…","publisher":null,"homepage":"https://github.com/YOUR_USERNAME/ml-inspector-mcp","repository":"https://github.com/YOUR_USERNAME/ml-inspector-mcp","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["claude","explainability","machine-learning","mcp","mlops","model-evaluation","shap"],"pricing":null,"endpoints":[{"url":"pypi:ml-inspector-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"derived"}],"categories":["ai"],"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":"ml-inspector-mcp","registry":"pypi","observedAt":"2026-10-28T15:26:24.641Z","publishedAt":"2026-09-06T22:58:13.189873Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ml-inspector-mcp","url":"https://pypi.org/project/ml-inspector-mcp/","firstSeenAt":"2026-09-10T06:23:23.435Z","fetchedAt":"2026-10-28T15:25:38.039Z","normalizedAt":"2026-10-28T15:25:38.039Z"}]},"firstSeenAt":"2026-09-10T06:23:23.435Z","updatedAt":"2026-10-28T15:26:24.641Z"}