{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_tyybnxqupk9q","handle":"sktime-mcp","url":"https://wellknown.network/agents/sktime-mcp","links":{"self":"https://wellknown.network/agents/sktime-mcp/record.json","html":"https://wellknown.network/agents/sktime-mcp","markdown":"https://wellknown.network/agents/sktime-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sktime-mcp","status":"https://wellknown.network/api/v1/agents/sktime-mcp/status","claim":"https://wellknown.network/agents/sktime-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sktime-mcp/claim.json","badge":"https://wellknown.network/agents/sktime-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sktime-mcp/history","tools":"https://wellknown.network/api/v1/agents/sktime-mcp/tools"},"ard":{"identifier":"urn:air::server:sktime-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sktime-mcp","summary":"MCP (Model Context Protocol) layer for sktime - Registry-Driven for LLMs","description":"# sktime-mcp\n\n**[Read the Documentation](http://sktime.github.io/sktime-mcp/)** | **[PyPI Package](https://pypi.org/project/sktime-mcp/0.1.0/)**\n\n**MCP (Model Context Protocol) layer for sktime - Registry-Driven for LLMs**\n\nA semantic engine that exposes sktime's native registry and semantics to Large Language Models, enabling them to:\n\n- 🔍 **Discover** valid estimators\n- 🧠 **Reason** about estimator capabilities  \n- 🔗 **Compose** compatible estimators\n- ⚡ **Execute** real sktime workflows on real data\n\n## 🎯 Design Philosophy\n\nThis MCP is **not** just documentation or static code analysis. It is a **semantic engine** for programmatic model usage.\n\n### Key Principles\n\n1. **sktime as Source of Truth** - No AST parsing, no repo indexing, no heuristics. All structure comes from `all_estimators`, estimator tags, and sktime's API contracts.\n\n2. **Registry-First** - Instead of `File → Class → Infer Relationships`, we do `Registry → Semantics → Safe Execution`.\n\n3. **Minimal MCP Surface** - Exposes only what an LLM needs: Discovery, Description, Instantiation, Execution, and model persistence.\n\n## 🛠️ Installation\n\n### Zero-install via uvx (recommended)\n\nIf you have [uv](https://github.com/astral-sh/uv) installed, no separate installation step is needed. Just update your MCP client config (see [Connecting from an LLM Client](#connecting-from-an-llm-client) below) and `uvx` will handle the rest automatically.\n\n```bash\n# Verify uv is available\nuvx sktime-mcp --help\n```\n\n### pip\n\n```bash\npip install sktime-mcp\n\n# With optional extras (SQL, forecasting models, file formats)\npip install \"sktime-mcp[all]\"\n```\n\n### Development installation\n\n```bash\ngit clone https://github.com/sktime/sktime-mcp\ncd sktime-mcp\npython3 -m pip install -e \".[dev]\"\n```\n\n### 🐳 Docker\n\nRun without installing anything locally (only Docker required):\n\n```bash\n# Build the image\ndocker build -t sktime-mcp .\n\n# Run the MCP server (stdio transport)\ndocker run -i sktime-mcp\n```\n\nOr use Docker Compose:\n\n```…","publisher":{"name":"sktime-mcp contributors","url":null},"homepage":null,"repository":null,"version":"0.1.1","license":"BSD 3-Clause License\n        \n        Copyright (c) 2026 - pres…","protocols":["mcp"],"tags":["forecasting","llm","machine-learning","mcp","sktime","time-series"],"pricing":null,"endpoints":[{"url":"pypi:sktime-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev"],"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":"sktime-mcp","registry":"pypi","observedAt":"2026-11-04T01:24:41.614Z","publishedAt":"2026-06-30T17:05:35.288705Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sktime-mcp","url":"https://pypi.org/project/sktime-mcp/","firstSeenAt":"2026-09-10T12:22:27.144Z","fetchedAt":"2026-11-04T01:22:25.253Z","normalizedAt":"2026-11-04T01:22:25.253Z"}]},"firstSeenAt":"2026-09-10T12:22:27.144Z","updatedAt":"2026-11-04T01:24:41.614Z"}