Evals
Request insights for an eval run
Changed onNo credits are consumed — the model cost is on MCPJam. Runs a model over the finished run and draws on the same shared insightsPerDay request ledger as swarm and user-testing insights.
202: scheduled, not done. Poll the run detail's insights envelope rather than re-requesting — the envelope's status distinguishes pending from not_requested, which a second POST would not.
post/projects/{projectId}/eval-runs/{runId}/insights
Request
- Base URLhttps://app.mcpjam.com/api/v1
- URLhttps://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/insights
- AuthHTTP bearer
Request body
Response
Scheduled.
Changes
- info
added the new optional
headerrequest parameterx-mcpjam-eval-vocabularyto all path's operations
- info
- info
added the non-success response with the status
- info