RedCrown.aiRedCrown.ai Docs Open the app

MCP reference

Every RedCrown MCP tool at mcp.redcrown.ai.

Core tools

ToolDescription
prove_taskBenchmark every model on a task and return the cheapest one that's good enough, with a shareable proof link. Pass a plain-language task and a few examples ({input, output?}); leave the output blank to rank against the model you use now. For a no-input demo, use try_sample.
try_sampleRun a benchmark on a public sample dataset and return a shareable proof, no input, no keys, no account. Great for a quick demo. Optional task (default: transcribe).
import_resultsTurn an eval you already ran (in any harness or the redcrown CLI) into a ranked, shareable run. Pass the aggregate results object (name, objective, quality_metric, quality_bar, step, candidates[, references]). Returns the experiment and run ids.
get_runGet an experiment run and its ranked report by run id.
get_reportAlias of get_run: fetch the ranked proof report for a run id.

Advanced tools

ToolDescription
list_modelsList available providers and models, including free no-key models.
list_experimentsList the caller's experiments.
create_experimentCreate an experiment from a full definition (name, objective, quality_metric, quality_bar, reference_source, allowed_providers, pipeline, dataset). Most callers should use prove_task instead.
run_experimentQueue a run of an experiment by id; returns the run id to poll with get_report.
scaffold_experimentTurn a plain-language task into a valid experiment spec ready for create_experiment. (prove_task does this for you.)
simulate_costEstimate projected hosted-API and self-hosted (per cloud) cost for a model and token counts.
setup_proxyCreate a proxied endpoint that captures live traffic for shadow evaluation. Returns the endpoint key and forward URL.
list_proxiesList all proxied endpoints for the caller's workspace.
replay_capturesReplay captured traffic through the shadow eval engine for a proxied endpoint.
create_reviewCreate a human-review session for a proxied endpoint's captures.
invite_reviewerInvite a reviewer to a review session. Returns a one-time token; the link is https://app.redcrown.ai/review/<token>.
get_review_examplesGet the candidate outputs for a captured request, ready for human review.
get_decision_reportGet the aggregated decision report for a review session, including reviewer verdicts and the recommended winner.

Generated from source. Last verified .