List a suite's runs

Recent runs for a suite, newest first.

GET /projects/{projectId}/eval-suites/{suiteId}/runs

List a suite's runs

cURL

curl --request GET \
  --url https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites/{suiteId}/runs \
  --header 'Authorization: Bearer <token>'

200

Example

{ "items": [ { "id": "<string>", "suiteId": "<string>", "status": "pending", "source": "ui", "createdAt": 123, "client": { "id": "<string>", "name": "<string>", "source": "environment", "hostStyle": "<string>", "modelId": "<string>" }, "runNumber": 123, "result": "passed", "summary": { "total": 123, "passed": 123, "failed": 123, "passRate": 123 }, "launcher": { "kind": "cli", "client": "<string>", "version": "<string>" }, "attribution": { "surface": "rest", "apiKeyId": "<string>" }, "notes": "<string>", "completedAt": 123, "scoreIntegrity": "valid", "verdictPolicyVersion": 2, "verdictSummary": {}, "verdictPolicyIntegrityError": "<string>", "environment": { "id": "<string>", "name": "<string>", "revision": 123 }, "runGroupId": "<string>", "effectiveModelId": "<string>", "modelSource": "client_default", "executionEngine": "<string>", "insights": { "schemaVersion": 1, "scope": { "kind": "eval_run", "id": "<string>", "runId": "<string>", "scenarioId": "<string>", "windowStartAt": 123, "windowEndAt": 123 }, "status": "not_available", "reasonCode": "<string>", "retryable": true, "error": { "code": "<string>", "message": "<string>" }, "generatedAt": 123, "updatedAt": 123, "summary": "<string>", "coverage": { "unit": "iterations", "analyzed": 123, "total": 123, "truncated": true, "lowConfidence": true, "gradedCount": 123, "feedbackCount": 123 }, "findings": [ { "id": "<string>", "signalFingerprint": "<string>", "title": "<string>", "category": "unknown", "attribution": "unknown", "actionTarget": "investigate", "actionability": "informational", "severity": "info", "confidence": "low", "observed": "<string>", "recommendation": "<string>", "acceptanceCriteria": [ "<string>" ], "affected": { "count": 123, "total": 123, "unit": "iterations" }, "evidence": [ { "kind": "tool_error", "excerpt": "<string>", "sessionId": "<string>", "iterationId": "<string>", "toolName": "<string>", "errorCode": "<string>" } ], "rootCause": "<string>", "patternSlug": "<string>", "target": { "serverId": "<string>", "surface": "description", "snapshotHash": "<string>", "toolName": "<string>", "fieldPath": "<string>", "currentDefinition": { "truncated": true, "description": "<string>", "inputSchemaJson": "<string>", "outputSchemaJson": "<string>" } } } ], "truncation": { "truncated": true, "omittedFindings": 123, "omittedEvidence": 123, "contractTruncated": true }, "currentFindings": [ { "id": "<string>", "signalFingerprint": "<string>", "title": "<string>", "category": "unknown", "attribution": "unknown", "actionTarget": "investigate", "actionability": "informational", "severity": "info", "confidence": "low", "observed": "<string>", "recommendation": "<string>", "acceptanceCriteria": [ "<string>" ], "affected": { "count": 123, "total": 123, "unit": "iterations" }, "evidence": [ { "kind": "tool_error", "excerpt": "<string>", "sessionId": "<string>", "iterationId": "<string>", "toolName": "<string>", "errorCode": "<string>" } ], "rootCause": "<string>", "patternSlug": "<string>", "target": { "serverId": "<string>", "surface": "description", "snapshotHash": "<string>", "toolName": "<string>", "fieldPath": "<string>", "currentDefinition": { "truncated": true, "description": "<string>", "inputSchemaJson": "<string>", "outputSchemaJson": "<string>" } } } ], "observationState": "ready", "observationCoverage": { "unit": "iterations", "analyzed": 123, "total": 123, "gradedCount": 123, "exclusions": {} }, "unifiedFindings": { "capability": "unified_findings_v1", "snapshot": {}, "job": {}, "canBuild": true, "canEnrich": true, "analysis": { "phase": "reading", "progress": { "done": 123, "total": 123, "unit": "iterations" }, "models": [ "<string>" ], "completeness": { "iterationReports": 123, "total": 123, "missingTraces": 123 } } }, "runHealth": { "targets": [ { "subjectKind": "environment", "subjectId": "<string>", "subjectLabel": "<string>", "attempted": 123, "succeeded": 123, "failed": 123, "rateLimited": 123 } ] } }, "judges": { "goalCompletion": { "status": "pending", "errorCode": "<string>", "summary": "<string>", "generatedAt": 123, "modelUsed": "<string>", "threshold": 123, "cases": [ { "caseKey": "<string>", "score": 123, "passed": true, "reason": "<string>", "rubricHits": [ "<string>" ], "status": "scored", "gradingKey": "<string>", "errorCode": "<string>", "judgeTemplateVersion": 123, "judgeTemplateHash": "<string>", "evidenceHash": "<string>", "evidenceManifest": { "version": 1, "traceComplete": true, "traceFields": [ "<string>" ], "messageCount": 123, "spanCount": 123, "artifactSources": [ { "sourceId": "<string>", "mediaType": "<string>", "modality": "image" } ], "uncaptured": [ "<string>" ], "inputBytes": 123 }, "iterationId": "<string>" } ], "progress": { "total": 123, "completed": 123, "errors": 123, "skipped": 123 }, "judgeTemplateVersion": 123, "judgeTemplateHash": "<string>" }, "groundedness": { "status": "pending", "errorCode": "<string>", "summary": "<string>", "generatedAt": 123, "modelUsed": "<string>", "threshold": 123, "cases": [ { "caseKey": "<string>", "score": 123, "passed": true, "reason": "<string>", "unsupportedClaims": [ "<string>" ], "iterationId": "<string>" } ] } }, "gateWaiver": { "id": "<string>", "suiteId": "<string>", "runId": "<string>", "reason": "<string>", "expiresAt": 123, "createdAt": 123, "createdBy": "<string>", "createdByEmail": "<string>", "revokedAt": 123, "revokedBy": "<string>", "active": true, "policySnapshot": { "minimumPassRate": 123 } }, "importEligibility": { "status": "legacy", "gateable": true, "importedCaseCount": 123, "claimedExactCaseIds": [ "<string>" ], "approvedApproximationCaseIds": [ "<string>" ], "approvedApproximationReceipts": [ { "testCaseId": "<string>", "approvedBy": "<string>", "approvedAt": 123, "reason": "<string>", "caseKey": "<string>", "sourceCaseKey": "<string>" } ], "issues": [ { "code": "<string>", "testCaseId": "<string>", "caseKey": "<string>", "toolName": "<string>" } ] }, "name": "<string>", "tags": [ "<string>" ], "runMetadata": {}, "ciMetadata": {}, "runEvaluationsByCase": [ {} ] } ] }

Authorizations

Authorization · string · header · required

MCPJam API key (sk_…). Create one at Settings → API keys. Guest sessions cannot use the API, and API keys cannot manage other API keys.

Headers

x-mcpjam-eval-vocabulary · enum<string>

Which vocabulary this request and its response speak. Absent means 1, which is byte-for-byte today's contract: the same request fields, the same refusals, the same response projection. 2 is the canonical vocabulary. Any other value is a 400 with code: "VALIDATION_ERROR".

Today it decides one thing: the spelling of an evaluator's policy role. Vocabulary 1 accepts and returns gating; vocabulary 2 accepts both spellings and returns the canonical required. Sending required without the header is a 400, deliberately — vocabulary 1 is not widened to meet vocabulary 2 half way, because a boundary that accepts a spelling it does not announce is one two implementations can disagree about.

A response that varies by vocabulary sends Vary: x-mcpjam-eval-vocabulary.

Available options: 1, 2

Path Parameters

projectId · string · required

ID of the hosted project that contains the server.

suiteId · string · required

Eval suite ID, as returned by POST /eval-runs.

Query Parameters

limit · integer · default: 25

Maximum runs to return, 1–100. Defaults to 25.

Required range: 1 <= x <= 100

Response

200

application/json

Recent runs, newest first.

items · object[] · required

Show child attributes