{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_jyp6dma2k9xt","handle":"solar-data-mcp-forecast","url":"https://wellknown.network/agents/solar-data-mcp-forecast","links":{"self":"https://wellknown.network/agents/solar-data-mcp-forecast/record.json","html":"https://wellknown.network/agents/solar-data-mcp-forecast","markdown":"https://wellknown.network/agents/solar-data-mcp-forecast/record.md","api":"https://wellknown.network/api/v1/agents/solar-data-mcp-forecast","status":"https://wellknown.network/api/v1/agents/solar-data-mcp-forecast/status","claim":"https://wellknown.network/agents/solar-data-mcp-forecast/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/solar-data-mcp-forecast/claim.json","badge":"https://wellknown.network/agents/solar-data-mcp-forecast/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/solar-data-mcp-forecast/history","tools":"https://wellknown.network/api/v1/agents/solar-data-mcp-forecast/tools"},"ard":{"identifier":"urn:air::server:solar-data-mcp-forecast","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"solar-data-mcp-forecast","summary":"MCP server for solar generation forecasts via the open Quartz Solar Forecast model (Open Climate Fix)","description":"# solar-data-mcp-forecast\n\nMCP server wrapping the open [Quartz Solar Forecast](https://github.com/openclimatefix/quartz-solar-forecast)\nmodel (Open Climate Fix) — the forecast domain of\n[solar-data-mcp](https://github.com/hoodsy/solar-data-mcp). No API key needed.\n\n| Tool | Answers |\n|---|---|\n| `forecast_generation` | \"What will my array generate tomorrow?\" (hourly, ≤48 h) |\n| `compare_forecast_to_model` | \"Is today unusually sunny?\" (forecast vs PVWatts typical-year) |\n\nRun standalone: `uvx --from solar-data-mcp-forecast solar-forecast-mcp` — but see the\nmodel-install note below; most users want the combined\n[`solar-data-mcp`](https://github.com/hoodsy/solar-data-mcp/blob/main/packages/solar-data-mcp/README.md)\nserver, which adds the other three domains plus the skill and report layer.\n\n## Installing the model\n\n`quartz-solar-forecast` pins `pydantic==2.6.2`, which conflicts with the MCP SDK,\nso it is not a declared dependency. Install it alongside (it runs fine on newer\npydantic; the pin is conservative). **Python 3.11 is required** —\n`pv-site-prediction` does not support 3.12+:\n\n```console\n$ uv venv --python 3.11 --seed .venv && source .venv/bin/activate\n$ pip install solar-data-mcp-forecast\n$ pip install --no-deps quartz-solar-forecast\n$ pip install pv-site-prediction xarray xgboost openmeteo-requests requests-cache retry-requests huggingface_hub async_timeout\n```\n\nOn macOS, xgboost also needs the OpenMP runtime: `brew install libomp`.\n\nWithout the model installed, the server still starts and its tools return an\nerror containing these instructions.\n\nModel note: Quartz is trained on sites ≤ 4 kWp; larger arrays are modeled at\n4 kWp and linearly scaled (the library prints a notice when it does this).\n\n## Using forecasts with the combined `solar-data-mcp` server\n\nAn ephemeral `uvx` environment cannot hold the side-install above. Use a\npersistent venv and point your agent at its entry point:\n\n```console\n$ uv venv --python 3.11 --seed ~/.venvs/solar-data-mcp\n$ ~/.v…","publisher":{"name":"Logan Bernard","url":null},"homepage":"https://github.com/hoodsy/solar-data-mcp","repository":"https://github.com/hoodsy/solar-data-mcp","version":"0.1.1","license":null,"protocols":["mcp"],"tags":["forecast","mcp","open-climate-fix","quartz","solar"],"pricing":null,"endpoints":[{"url":"pypi:solar-data-mcp-forecast","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":"data.weather","name":"Weather","confidence":1,"provenance":"declared"},{"slug":"ai.model-access","name":"Model Access","confidence":0.905,"provenance":"derived"}],"categories":["ai","data"],"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":"solar-data-mcp-forecast","registry":"pypi","observedAt":"2026-11-04T01:24:46.306Z","publishedAt":"2026-07-06T20:15:19.395629Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"solar-data-mcp-forecast","url":"https://pypi.org/project/solar-data-mcp-forecast/","firstSeenAt":"2026-09-10T12:22:52.523Z","fetchedAt":"2026-11-04T01:22:51.812Z","normalizedAt":"2026-11-04T01:22:51.812Z"}]},"firstSeenAt":"2026-09-10T12:22:52.523Z","updatedAt":"2026-11-04T01:24:46.306Z"}