Chronulus AI MCP Server
OfficialChat with Chronulus AI forecasting and prediction agents directly from Claude.
Add to your client
Copy the config for your MCP client and paste it into its config file.
pip install chronulus-mcpPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"chronulus-ai-mcp-server": {
"command": "uvx",
"args": [
"chronulus-mcp"
],
"env": {
"CHRONULUS_API_KEY": "<YOUR_CHRONULUS_API_KEY>"
}
}
}
}Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.
Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- A Chronulus API key (CHRONULUS_API_KEY)
- Python 3.10+ (when installed via pip), or uv/uvx, or Docker
- An MCP client such as Claude for Desktop
About Chronulus AI MCP Server
Chronulus MCP exposes the Chronulus AI forecasting and prediction platform to MCP clients like Claude for Desktop. A session captures an overall use case (a situation plus a task); agents are created against a session and are reusable across multiple inputs. The NormalizedForecaster agent produces forecasts of values between 0 and 1 (interpretable as seasonal weights, probabilities, or shares) without requiring historical data, while the BinaryPredictor agent estimates the probability of binary outcomes using a configurable panel of 2 to 30 experts and returns Beta-distribution parameters for confidence intervals. Additional tools rescale forecasts, save forecasts to CSV/TXT, save a binary-prediction analysis to HTML, and retrieve a risk-assessment scorecard. The server runs over stdio and can be installed via pip, uvx, or Docker.
Tools & capabilities (9)
create_chronulus_sessionCreates a new Chronulus session from a situation and task describing the forecasting/prediction use case and returns a reusable session_id.
create_forecasting_agent_and_get_forecastCreates a NormalizedForecaster agent with a session and input data model, submits forecast input data, and returns prediction data (values between 0 and 1) plus a text explanation.
reuse_forecasting_agent_and_get_forecastSubmits new forecast input to a previously created NormalizedForecaster agent (unchanged input data model) and returns prediction data and a text explanation.
rescale_forecastRescales NormalizedForecaster predictions (values between 0 and 1) to a use-case-specific min/max, with optional inverse scaling.
save_forecastSaves a NormalizedForecaster forecast to separate CSV (data) and TXT (explanation) files, with optional rescaling via y_min/y_max and invert_scale.
create_prediction_agent_and_get_predictionsCreates a BinaryPredictor agent with a session and input data model, submits prediction input, and returns a consensus probability from a panel of experts plus individual estimates, explanations, and Beta-distribution alpha/beta parameters.
reuse_prediction_agent_and_get_predictionSubmits new prediction input to a previously created BinaryPredictor agent (unchanged input data model) and returns the consensus probability, expert estimates, explanations, and Beta-distribution parameters.
save_prediction_analysis_htmlSaves a BinaryPredictor prediction analysis to an HTML file, including a plot of the theoretical and empirical Beta distribution and the experts' opinions.
get_risk_assessment_scorecardRetrieves the risk-assessment scorecard for a Chronulus session in Markdown format to surface risk level and safety concerns of a use case.
When to use it
- Retail demand forecasting and estimating share of foot traffic or out-of-stock probability
- Estimating the probability of binary events using a panel of expert agents with confidence intervals
- Producing forecasts from mixed text, image, and PDF inputs without historical time-series data
- Generating and saving forecast data, explanations, and risk-assessment scorecards for analysis
Security notes
Requires a Chronulus API key supplied via the CHRONULUS_API_KEY environment variable. Inputs (text and files) are sent to the Chronulus AI cloud platform for processing; total input size cannot exceed 10MB.
Chronulus AI MCP Server FAQ
How do I authenticate with Chronulus?
Set the CHRONULUS_API_KEY environment variable in your MCP client config to your Chronulus API key.
What input formats can I pass to the agents?
You can pass plain text or files by path, including images, text files, and PDFs (via input types such as ImageFromFile, TextFromFile, and PdfFromFile). The total size of all inputs cannot exceed 10MB.
Do I need historical data to forecast?
No. Both the NormalizedForecaster and BinaryPredictor agents are designed to produce forecasts and probability estimates without requiring historical data.
How do I install and run the server?
You can install it from PyPI with 'pip install chronulus-mcp', run it via uvx ('uvx chronulus-mcp'), or build and run the provided Docker image. Then add the corresponding mcpServers entry to your claude_desktop_config.json.
Alternatives to Chronulus AI MCP Server
Compare all alternatives →
Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.
Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.
Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.
Compare Chronulus AI MCP Server with: