MCP reference
Every RedCrown MCP tool at mcp.redcrown.ai.
Core tools
| Tool | Description |
|---|---|
prove_task | Run a task against several models on your examples and rank them against your quality bar. Pass a plain-language task and a few examples ({input, output?}); leave output blank to rank against the model you use now. Returns the ranking, the report's caveats and evidence issues. Set publish: true to also create a share link; on the Free plan that uses the one hosted proof. When the scoring method is not clear, the tool runs nothing. It returns status needs_confirmation, the proposed method and the eligible options. To confirm, call again with quality_metric. For a stored example, use try_sample. |
try_sample | Return a stored example report (no input, no keys, no new run), with its ranking and caveats. Use it to see the report shape. Optional task (default: transcribe). |
import_results | Turn 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]). Also accepts a `redcrown harness export` payload: quality_metric `checks`, one candidate, per-item `checks` on each receipt. Returns the experiment and run ids. |
get_run | Get an experiment run and its ranked report by run id. |
get_report | Alias of get_run: fetch the ranked proof report for a run id. A checks report (a pushed harness run) carries per-item `checks` and a worst-first checks summary instead of a model ranking. |
Advanced tools
| Tool | Description |
|---|---|
list_models | List available providers and models, including free no-key models. |
list_experiments | List the caller's experiments. |
create_experiment | Create 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_experiment | Queue a run of an experiment by id; returns the run id to poll with get_report. |
scaffold_experiment | Turn a plain-language task into a valid experiment spec ready for create_experiment. (prove_task does this for you.) The response adds metric_options and metric_confirmation. When metric_confirmation.needed is true, pick an eligible metric and call again with quality_metric before create_experiment. |
simulate_cost | Estimate projected hosted-API and self-hosted (per cloud) cost for a model and token counts. |
setup_proxy | Create a proxied endpoint that captures live traffic for shadow evaluation. Returns the endpoint key and forward URL. |
list_proxies | List all proxied endpoints for the caller's workspace. |
replay_captures | Replay captured traffic through the shadow eval engine for a proxied endpoint. |
create_review | Create a human-review session for a proxied endpoint's captures. |
invite_reviewer | Invite a reviewer to a review session. Returns a one-time token; the link is https://app.redcrown.ai/review/<token>. |
get_review_examples | Get the candidate outputs for a captured request, ready for human review. |
get_decision_report | Get the aggregated decision report for a review session, including reviewer verdicts and the recommended winner. |
Generated from source. Last verified .