Forecall
Docs

Docs

How Forecall works and how to use it: what it measures, how to get your tools/list, how to read the scores and how to score from the command line.

  1. Getting started

    What Forecall measures, what you can do for free, including the Failure KB for your agents, what the paid plans add, and what static scoring cannot tell.

  2. Get your tools/list

    The JSON Forecall scores, the shapes and limits it accepts, and how to get it from your MCP server with forecall dump or the official SDKs.

  3. Read your scores

    How a tool's score out of 100 is made, what the checks across the server look for, and every issue code with its severity.

  4. Score with the CLI

    Score a tools/list file on your own machine with forecall lint, get it from your server with forecall dump, connect your AI clients to the Failure KB with forecall setup, and use them in CI.

  5. Keep your server's scores

    Register your MCP server in the dashboard, keep a scored version each time its tools change, compare versions, and import a result from the linter.

  6. Evaluate your server with models

    Run an evaluation of your registered MCP server in the dashboard, and read it: how the cases are written, the distractor servers, what the metrics mean, and how the units are counted.

  7. Failure KB for your agents

    Connect your AI agent to the Failure KB, the MCP server of known MCP tool failures and their workarounds: its four tools, how records get verified, what is redacted, and the limits.

  8. API keys and the REST API

    Create an API key in the dashboard, save your registered server's scores from CI and run its evaluations with the REST API, its endpoints, limits and errors.

  9. Plans and billing

    The Free, Pro and Team plans and what each includes, how units and credits are counted, and how to subscribe, change plans, cancel and handle a failed payment.