Metadata-Version: 2.5
Name: precog-mcp
Version: 1.3.0
Summary: MCP server exposing Precog forecasts as tools.
Project-URL: Homepage, https://github.com/Albe83/precog
Project-URL: Repository, https://github.com/Albe83/precog
Project-URL: Issues, https://github.com/Albe83/precog/issues
Project-URL: Changelog, https://github.com/Albe83/precog/blob/main/CHANGELOG.md
License: MIT
Keywords: forecasting,mcp,time-series,timesfm
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.12
Requires-Dist: httpx>=0.27
Requires-Dist: mcp>=2.2
Requires-Dist: precog-client<0.2.0,>=0.1.0
Requires-Dist: precog-schemas<0.2.0,>=0.1.0
Requires-Dist: prometheus-client>=0.20
Requires-Dist: pydantic-settings>=2.4
Requires-Dist: pydantic>=2.7
Requires-Dist: uvicorn[standard]>=0.30
Provides-Extra: otel
Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.27; extra == 'otel'
Requires-Dist: opentelemetry-instrumentation-httpx>=0.48b0; extra == 'otel'
Requires-Dist: opentelemetry-sdk>=1.27; extra == 'otel'
Description-Content-Type: text/markdown

# precog-mcp

MCP server exposing Precog zero-shot forecasting to agents as the semantic
`forecast` and `backtest` tools plus the `precog://capabilities` resource.

It talks to the Precog **REST Execution API** over HTTP through the official
`precog-client` and contains **no model weights**.

## Install

```bash
pip install precog-mcp
```

## Run

```bash
# stdio transport
PRECOG_API_URL=http://localhost:8000 precog-mcp

# HTTP transport (endpoint: http://localhost:8765/mcp)
PRECOG_MCP_TRANSPORT=http PRECOG_MCP_PORT=8765 \
  PRECOG_API_URL=http://localhost:8000 precog-mcp
```

The API must be reachable; see `precog-api` or the container/Helm deployment.

## License

MIT.
