> ## Documentation Index > Fetch the complete documentation index at: https://mcpjam-mintlify-docs-update-pr-4615-1788458430079.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # List run iterations > Per-iteration results: actual tool calls, structured token usage, and latency. Cursor-paginated. ## OpenAPI ````yaml /reference/openapi.json get /projects/{projectId}/eval-runs/{runId}/iterations openapi: 3.1.0 info: title: MCPJam API version: 1.0.0-preview description: >- Programmatic access to MCP servers saved in your MCPJam projects — live diagnostics (validate, inspect, export) and operations: call tools, render prompts, run eval suites asynchronously and poll their results, and import OAuth tokens. **The API is in preview**: the surface may change while we finish the design. Error `code` values are stable; error `message` strings are not. Write clients that ignore unknown response fields. contact: name: MCPJam url: https://github.com/MCPJam/inspector/issues servers: - url: https://app.mcpjam.com/api/v1 description: Hosted MCPJam security: - bearerAuth: [] tags: - name: Agent browsers description: >- Isolated cloud browser sessions for coding agents. Requires authenticated project membership and a configured desktop runtime. - name: Clients description: >- Clients — the named, reusable configurations that define how MCPJam connects to and talks to your MCP servers. The original `/hosts` paths remain as deprecated, ID-only compatibility aliases with their original DTOs and their original (tokenless) write contracts; every alias response carries `Deprecation: true`. New integrations should use `/clients`. - name: Environments description: >- Project environments: named, live-editable execution bundles (one host, an optional standalone server group, optionally pinned skills and plugin versions) that eval suites and journeys run against. Distinct from Sandbox images, which are Computer base images. Reads require project membership; every write requires project admin. - name: Plugins description: >- Agent Plugins imported into a project — read-only inventory and version detail. - name: Skills description: >- Cloud Skills: authored SKILL.md files stored in a project. Read-only here. Environments pin skills by id (`skillSelection.skillIds`) and eval runs pin them with `--compose-skill`, so this surface exists to give an unattended caller those ids; authoring is an app flow behind a beta gate. - name: Sandbox images description: >- Custom Computer images: a digest-pinned Dockerfile built into an immutable image your project's computers boot from. - name: Server diagnostics description: Connect-level health checks against a saved MCP server. - name: Primitives description: 'The server''s MCP primitives: tools, prompts, and resources.' - name: Export description: Full-server snapshots for diffing and CI. - name: Execution description: 'Run the server''s primitives: call tools, render prompts.' - name: Eval runs description: >- Asynchronous eval suite runs: create with 202, poll status, iterations, and traces. - name: Conformance runs description: >- Ingest MCP spec-conformance results from the SDK/CLI into project-owned history. Distinct from Eval runs (authored LLM cases) and from directory readiness. - name: Server connections description: >- Connect an MCP server URL to a project, authorizing in a browser when the server requires it. - name: OAuth description: 'Bring-your-own OAuth: import externally obtained tokens for a server.' - name: Scenarios description: >- Read-only access to the scenarios published from a project: listing, settings, attached servers, and share links. - name: Catalog description: >- Discover the resources the other routes operate on: your account, projects, servers, eval suites, and chat sessions. - name: Tunnels description: >- Relay tunnels that expose local MCP servers through a public URL, registered as first-class project servers (the `mcpjam cloud tunnel` CLI flow). - name: Agent description: >- Headless agent turns over the public API: send a message history, the server runs one assistant turn with project-scoped workspace tools (eval reads + suite creation) on a pinned hosted model, and returns the reply plus created-resource references. - name: Swarms description: >- Personas, journeys and swarm containers — the authoring half of Swarms — plus the model-backed generation that drafts them. - name: Swarm runs description: >- Launching journeys and reading what they produced. Launching SPENDS — see the per-operation notes. - name: Swarm insights description: >- What a swarm run revealed. The scorecard and findings are deterministic and free; requesting wave insights runs models and draws on your shared daily ledger. - name: User testing description: >- Publishing an environment for real visitors, and controlling who can reach it. Several of these NARROW access and take effect immediately. - name: Directory readiness description: >- Grade a saved server against a publisher's listing requirements: Anthropic's connector directory or OpenAI's plugin directory. Reported as lane status and coverage, never as a numeric score, and excluded from `pooledConformanceScore`. Deterministic grading is free; model-backed experience observations are an explicit opt-in that consumes MCPJam credits and can never decide a verdict. - name: Registry description: >- Search the scraped MCP directories (Claude, ChatGPT, and any future source), list curated/org registry cards, and install them into a project. Install writes a `servers` row and provenance — it does not open a live session. There is no catalog-uninstall route: delete the project server instead. Directory reads require a bearer (including minted guest tokens) but do not materialize a user. Card/connection reads and all writes are authed-non-guest. paths: /projects/{projectId}/eval-runs/{runId}/iterations: get: tags: - Eval runs summary: List run iterations description: >- Per-iteration results: actual tool calls, structured token usage, and latency. Cursor-paginated. operationId: listEvalRunIterations parameters: - $ref: '#/components/parameters/projectId' - $ref: '#/components/parameters/runId' - name: limit in: query required: false description: Page size, 1–200. Defaults to 50. schema: type: integer minimum: 1 maximum: 200 default: 50 - name: cursor in: query required: false description: Opaque cursor from a previous response's `nextCursor`. schema: type: string responses: '200': description: One page of iterations. content: application/json: schema: $ref: '#/components/schemas/EvalIterationPage' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' components: parameters: projectId: name: projectId in: path required: true description: ID of the hosted project that contains the server. schema: type: string runId: name: runId in: path required: true description: Eval run ID, as returned by `POST /eval-runs`. schema: type: string schemas: EvalIterationPage: type: object required: - items properties: items: type: array items: $ref: '#/components/schemas/EvalIteration' nextCursor: type: string description: Opaque cursor for the next page. Omitted on the last page. EvalIteration: type: object required: - id - iterationNumber - status - expectedToolCalls - actualToolCalls properties: id: type: string testCaseId: type: - string - 'null' description: >- The STORED case row's database id. Changes if the case is recreated and means nothing outside this deployment; see `caseId` for the declared one. caseId: type: string description: >- The case's SDK-DECLARED id, read from the iteration's frozen `testCaseSnapshot` — the durable, author-chosen identity that survives the case row being recreated. ABSENT on a UI-authored case (which never declared one) and on runs predating declared ids; absence is not an error. Distinct from `testCaseId`, which is this deployment's row id, and NOT a join key into `verdictSummary.cases[].caseId`, which is a separately encoded identity the platform mints from whichever spelling the run knew. title: type: - string - 'null' iterationNumber: type: integer status: type: string description: >- LIFECYCLE, not verdict: how far the trial got, never how it graded. A trial that ran normally and graded badly is `completed` with `result: "failed"`, so reading `status === "failed"` as "the case failed" counts harness noise as server defects. `failed` is an execution failure, `setup_failed` means the environment never came up, `timed_out` means the budget expired, `skipped` means it was deliberately not run, `cancelled` means it was withdrawn mid-flight (and is excluded from validity denominators). Treat an unrecognised value as non-terminal-unknown rather than as a failure. enum: - pending - running - completed - failed - cancelled - timed_out - setup_failed - skipped result: type: - string - 'null' description: >- Task verdict for the trial, independent of `status`. `null` until the trial is graded — including on a terminal trial that never produced a gradeable outcome (`setup_failed`, `skipped`). enum: - passed - failed - null model: type: - string - 'null' provider: type: - string - 'null' startedAt: type: - number - 'null' description: Epoch milliseconds. durationMs: type: - number - 'null' description: Wall-clock duration; `null` until terminal. tokensUsed: type: - number - 'null' usage: type: - object - 'null' description: >- Structured token usage (input/output/cached/reasoning) when available, plus `estimatedCostUsd` and the `costBasis` it was priced from. `estimatedCostUsd` ABSENT means no cost was observed — never that the trial was free. `costBasis.reason` says which: `no_pricing` (not an MCPJam-billed model, e.g. your own API key), `harness_mixed_models` (a harness turn mixes models and carries no per-model split, so its cost arrives with billed attribution instead), or `no_tokens`. `costBasis.source` is `gateway_pricing` when MCPJam priced its own token counts, and `sdk_runner` when the figure came from your runner — real, but neither computed nor verified by MCPJam. additionalProperties: true actualToolCalls: type: array items: type: object additionalProperties: true expectedToolCalls: type: array items: type: object additionalProperties: true error: type: - string - 'null' scores: type: - array - 'null' description: >- Per-scorer verdicts for this iteration. `null` when the run predates scoring, or when the stored payload failed validation at the boundary — partially-trusted score data is never projected. items: $ref: '#/components/schemas/ScoreResult' evaluationConfig: description: >- The scorer definitions `scores` were produced under. Present exactly when `scores` is: results carry only a `definitionHash`, so without this a caller cannot tell a gating failure from an advisory one. oneOf: - $ref: '#/components/schemas/EvaluationConfigSnapshot' - type: 'null' scoreIntegrity: type: - string - 'null' description: >- Set when the backend downgraded this iteration's verdict because its gating score evidence was malformed. enum: - score_integrity_invalid - null stageResults: type: array description: >- The user-value chain rows for this trial, in chain order, from a derivation that validated. items: $ref: '#/components/schemas/StageResultRow' firstFailedStage: type: string enum: - connection - discovery - selection - call - response - userValue description: >- Where the chain stopped — A LOCATION, NOT A CAUSE. It names the first link that failed, never why it failed: the why is `reason` on that stage's row (see `StageResultRow.reason`), and neither this nor the `failureCategory` bucket on its own authorizes proposing a change to the server. Absent when nothing failed — and absent on a trial that never reached a stage at all, such as a setup abort or an evaluator error, which still carries a `failureCategory`. `connection` — the server was reachable and the session initialized. `discovery` — its tools and resources were listed and readable. `selection` — the model chose the right tool for the request. `call` — the call was made with usable arguments. `response` — the server returned data the model could use. `userValue` — the user's actual request was satisfied. failureCategory: type: string enum: - setup - metadata - selection - arguments - serverData - userValue - evaluator description: >- The bucket this trial is grouped under — A BUCKET, NOT A DIAGNOSIS. Present without `firstFailedStage` for a trial that never reached a stage. `setup` — setup: the harness or environment never got to the test. `metadata` — tool metadata: tool names, descriptions or schemas misled the model. `selection` — tool selection: the model picked the wrong tool, or none. `arguments` — call arguments: the right tool, called wrongly. `serverData` — server data: the server answered, with data the model could not use. `userValue` — user value: everything mechanical worked and the user still was not served. `evaluator` — evaluator: the grader itself failed, so the run says nothing about the server — never folded into the others, because counting a broken judge as a server defect poisons every rate derived from it. stageAnalyzerVersion: type: integer minimum: 0 stageResultsUnverified: type: boolean enum: - true frictionSignals: $ref: '#/components/schemas/EvalTrialFrictionSignals' frictionSignalsUnverified: type: boolean enum: - true description: >- The server stored a friction document that failed validation. The signals themselves are withheld rather than partially trusted. suspectedConditionVerdict: $ref: '#/components/schemas/EvalSuspectedConditionVerdict' suspectedConditionUnverified: type: boolean enum: - true description: >- The server stored a suspected-condition verdict that failed validation. The verdict is withheld rather than partially trusted. Error: type: object required: - code - message properties: code: type: string description: >- Stable, machine-readable error code. New codes may be added over time; treat unknown codes as non-retryable failures unless the HTTP status says otherwise. enum: - UNAUTHORIZED - FORBIDDEN - NOT_FOUND - CONFLICT - VALIDATION_ERROR - RATE_LIMITED - FEATURE_NOT_SUPPORTED - SERVER_UNREACHABLE - TIMEOUT - OAUTH_REQUIRED - INTERNAL_ERROR message: type: string description: >- Human-readable description. May change between releases — don't match on it. details: type: object description: Optional, unstructured context bag. additionalProperties: true ScoreResult: type: object description: >- One scorer's verdict for one iteration. `passed` is DERIVED as `value >= passThreshold` — never asserted by the scorer or the model. required: - scorerId - scorerVersion - definitionHash - status - passThreshold - deterministic properties: scorerId: type: string maxLength: 128 scorerVersion: type: string definitionHash: type: string description: >- Joins this result to its definition in `evaluationConfig.definitions`. status: type: string description: >- `error` is never a low score — a crashed judge is not a disagreeing judge. `not_applicable` never gates and is excluded from aggregation denominators, which is what distinguishes it from `skipped`. enum: - scored - error - skipped - not_applicable value: type: number minimum: 0 maximum: 1 description: Present only when `status` is `scored`. passThreshold: type: number minimum: 0 maximum: 1 passed: type: boolean description: >- Derived as `value >= passThreshold`; present only when `status` is `scored`. rationale: type: string maxLength: 2000 evidence: type: array maxItems: 20 items: type: string maxLength: 300 deterministic: type: boolean model: type: string promptHash: type: string error: type: string maxLength: 500 description: Present only when `status` is `error`. scope: type: object description: >- Absent means case-level; `{kind:"turn",promptIndex}` means the check was authored on a single turn. additionalProperties: true EvaluationConfigSnapshot: type: object description: >- The scorer definitions a run graded with, plus their hash. Changing scorer configuration changes this hash but NOT the case identity — a threshold edit must not fork a scenario's history. required: - hash - definitions properties: hash: type: string description: >- `evaluationConfigHash` over the resolved definitions. Order-independent — the hash sorts internally. definitions: type: array items: $ref: '#/components/schemas/ResolvedScoreDefinition' StageResultRow: type: object description: >- One user-value stage's verdict for one trial, from a derivation that validated. Six of these make a chain, always in chain order, and the order is normative: `notReached` is derived from position, so re-ordering them changes which stages a failure is said to have blocked. required: - stage - state properties: stage: type: string enum: - connection - discovery - selection - call - response - userValue description: >- Which link of the user-value chain this row is a verdict on. The order is NORMATIVE: a run walks the six in sequence, and `notReached` is derived from position — every stage after the first failed one never ran. `connection` — the server was reachable and the session initialized. `discovery` — its tools and resources were listed and readable. `selection` — the model chose the right tool for the request. `call` — the call was made with usable arguments. `response` — the server returned data the model could use. `userValue` — the user's actual request was satisfied. state: type: string enum: - passed - failed - notReached - notMeasured - notApplicable description: >- What this stage did. The three non-verdicts stay three different facts on purpose: collapsing them is how "we never checked" gets read as "it passed". `passed` — measured, and it passed. `failed` — measured, and it failed. `notReached` — it never ran (an earlier stage failed), so there was nothing to decide. `notMeasured` — this run captured nothing that could decide it, so the stage is not measured. `notApplicable` — the stage is not applicable to this case at all. reason: type: string enum: - noSpanChannel - noEvidenceCaptured - matchVerdictUnavailable - traceAbsent - executorEmitsNoSpans - blockedByPolicy - evaluatorError - providerError - setupAborted - connectFailed - toolsListFailed - egressUnverified - lifecycleStopped - notAuthored - earlierStageFailed - missingToolCall - unexpectedToolCall - argumentMismatch - toolError - protocolError - renderFailed - predicateFailed - observed - impliedByLaterEvidence - judgeObserved - judgePartial - judgeFailed - judgePending - judgeNotRequested description: >- Why this stage landed where it did. A CLOSED vocabulary — render what arrives, never widen it. Each entry completes "…because ". `noSpanChannel` — this run captures no evidence channel for that stage. `noEvidenceCaptured` — nothing eligible for that stage was captured. `matchVerdictUnavailable` — extra tool calls were captured but the run did not report whether its match options tolerate them. `traceAbsent` — the iteration recorded no trace. `executorEmitsNoSpans` — the executor emitted no spans. `blockedByPolicy` — a policy blocked the run before it could be measured. `evaluatorError` — the evaluator itself failed, so the run says nothing about the server. `providerError` — the model provider failed the call, so this stage was never measured. `setupAborted` — the environment was never prepared, so the test never began. `connectFailed` — the configured server was reached and initialize failed there. `toolsListFailed` — initialize succeeded and listing tools failed. `egressUnverified` — the connection failed with no evidence that our own network egress works. `lifecycleStopped` — the run was stopped mid-flight. `notAuthored` — the case asserts nothing this stage could decide. `earlierStageFailed` — an earlier stage failed. `missingToolCall` — an expected tool call was never made. `unexpectedToolCall` — a tool call was made that the case did not expect. `argumentMismatch` — the call arguments did not match what the case expects. `toolError` — the server reported a tool error. `protocolError` — the call never produced a result. `renderFailed` — the widget did not render. `predicateFailed` — a check on the result did not hold. `observed` — the evidence was inspected and the stage held. `impliedByLaterEvidence` — a later stage's success implies it. `judgeObserved` — the LLM judge scored at or above the threshold. `judgePartial` — the LLM judge scored inside the partial band — at or above the floor, below the threshold. `judgeFailed` — the LLM judge scored below the partial floor. `judgePending` — an LLM judge verdict is owed and has not arrived. `judgeNotRequested` — no LLM judge verdict was ever owed. evidence: type: object properties: spanIds: type: array items: type: string maxItems: 5 promptIndexes: type: array items: type: integer maxItems: 5 predicateReasons: type: array items: type: string maxLength: 500 maxItems: 5 additionalProperties: false EvalTrialFrictionSignals: type: object description: >- Observable patterns in one trial's tool calls. REPORT-ONLY: nothing here decided the trial's `result`, and every pattern has a benign reading. `state` is `notMeasured` when the trial could not be looked at at all; `identifierSignals.state` is separate because a trial whose tool results were not retained still has measurable retries but cannot be asked whether an identifier went unused. An ABSENT document means the trial predates the measurement — never read it as zero. required: - version - state - callCount - resultAvailableCount - timedCallCount - identifierSignals - signals properties: version: type: integer enum: - 1 description: >- Derivation semantics version. Bumped when a counting RULE changes, even if the shape does not. state: type: string enum: - measured - notMeasured notMeasuredReason: type: string enum: - noToolCalls - resultsUnavailable - orderingUnknown - evidenceIncomplete - truncated description: >- Present only when `state` is `notMeasured`. `noToolCalls` — no tool calls to look at. `resultsUnavailable` — tool results were not retained. `orderingUnknown` — the calls cannot be placed in a causal order. `evidenceIncomplete` — the evidence for this trial has a known hole. `truncated` — too many tool calls to measure. callCount: type: integer minimum: 0 resultAvailableCount: type: integer minimum: 0 timedCallCount: type: integer minimum: 0 identifierSignals: type: object description: >- Whether the two identifier-dependent kinds were measured at all. `notMeasured` here beside `state: measured` above is the normal shape for a run whose tool results were not retained: the retries were measured, the identifiers were never looked for. required: - state properties: state: type: string enum: - measured - notMeasured reason: type: string description: >- Why the identifier kinds were not measured. `noToolCalls` — no tool calls to look at. `resultsUnavailable` — tool results were not retained. `orderingUnknown` — the calls cannot be placed in a causal order. `evidenceIncomplete` — the evidence for this trial has a known hole. `truncated` — too many tool calls to measure. enum: - noToolCalls - resultsUnavailable - orderingUnknown - evidenceIncomplete - truncated signals: type: array maxItems: 24 items: $ref: '#/components/schemas/EvalFrictionSignal' description: >- Ordered by the call that made each pattern observable. Empty on a `measured` document means nothing fired; empty on a `notMeasured` one means nothing was looked for. EvalSuspectedConditionVerdict: type: object description: >- Which server-controlled condition is SUSPECTED of contributing to one observed friction pattern, from an advisory per-trial judge. REPORT-ONLY and NEVER a claim about cause: nothing here entered the trial’s `result`, its stage chain or its `failureCategory`, and only a controlled rewrite that changes the suspected response and holds the rest comparable could establish causation. ABSENT means no judge ran — the trial predates it, nothing was flagged, or the deployment has it off. required: - status - gradingKey - signalKind - informationCallIndex - observedAtCallIndex - judgeTemplateVersion - judgeTemplateHash - model - generatedAt properties: status: type: string enum: - scored - skipped - error description: >- `scored` — a verdict was produced. `skipped` — the judge did not reach this trial; `reason` says why. `error` — the pass threw for this trial. A skipped or errored trial carries NO condition, so “we never looked” is never rendered as “we looked and could not say”. reason: type: string enum: - spendBlocked - traceIncomplete - noEvidence - cap description: >- Present only when `status` is `skipped`. `spendBlocked` — the internal-LLM spend gate refused the call. `traceIncomplete` — a referenced trace blob could not be read. `noEvidence` — the judge’s window could not be built, most often because the information call’s result never reached the trace. `cap` — the run had more flagged trials than the per-run cap. condition: type: string enum: - unclear - idBuriedInPayload - idNameCollision - missingQueryEcho - silentTruncation - ambiguousErrorSemantics - missingUnits - responseWasClear - descriptionMisleading description: >- Which server-controlled condition is SUSPECTED of contributing. A CLOSED vocabulary. SUSPECTED, not established: the judge saw one window of one trial and named a plausible contributor, and only a controlled rewrite could turn that into a claim about cause. `unclear` — could not attribute: the judge could not identify a condition from what it was shown, which is also where a low-confidence or unsupported verdict is demoted to. `idBuriedInPayload` — identifier buried in payload: the identifier a later call needed was not where a caller would look for it. `idNameCollision` — identifier name collision: two different identifiers share a name, or one name means different things across tools. `missingQueryEcho` — response does not echo the query: a caller cannot tell a narrowed result from a fresh one. `silentTruncation` — response truncated without saying so. `ambiguousErrorSemantics` — error text does not say whether to retry. `missingUnits` — value has no stated unit. `responseWasClear` — the response was clear: the server's output does not explain the pattern. This is the honest negative and a real answer. `descriptionMisleading` — tool description points the wrong way. confidence: type: string enum: - low - medium - high description: >- How sure the judge was. `low` — low confidence: never reaches a reader as a named condition, because a low-confidence verdict is demoted to `unclear` before it is persisted. `medium` — medium confidence. `high` — high confidence. remediation: type: string maxLength: 300 description: >- ONE sentence naming a lever the SERVER OWNER controls. Absent for `unclear` and `responseWasClear`, which name no server problem to remediate, and absent from any verdict whose remediation named no server lever — that verdict is demoted to `unclear`. evidence: type: object description: >- Where in the window the judge was pointing. Dropped rather than guessed when it fell outside the window or named the wrong tool; the verdict survives, the pointer does not. required: - callIndex - toolName properties: callIndex: type: integer minimum: 0 toolName: type: string fieldPath: type: string maxLength: 120 gradingKey: type: string signalKind: type: string description: The friction signal that triggered the judge. informationCallIndex: type: integer minimum: 0 description: >- Where the information was surfaced. The judge saw calls 0 through `observedAtCallIndex` and nothing after. observedAtCallIndex: type: integer minimum: 0 description: >- The call that made the pattern observable, and the judge’s evidence bound. judgeTemplateVersion: type: integer minimum: 1 judgeTemplateHash: type: string model: type: string generatedAt: type: integer minimum: 0 ResolvedScoreDefinition: type: object description: >- A scorer definition with every semantic default resolved. This is the form that is hashed, so an omitted `onError` and an explicitly-configured default digest identically. required: - scorerId - idSource - scorerVersion - implementationHash - deterministic - passThreshold - role - onError - onSkipped properties: scorerId: type: string maxLength: 128 idSource: type: string description: >- `generated` ids are positional and UNSTABLE across config edits; only `explicit` ids may be referenced by a gate policy or tracked across runs. enum: - explicit - generated scorerVersion: type: string implementationHash: type: string description: >- Digest of what the scorer actually does — the canonicalized predicate, or the judge prompt plus template version. Required so two judges with different prompts cannot hash identically. label: type: string description: Presentation only; deliberately excluded from the hash. deterministic: type: boolean passThreshold: type: number minimum: 0 maximum: 1 role: type: string description: Only `gating` scorers decide the iteration's verdict. enum: - gating - advisory onError: type: string description: >- What an `error` status does to a gating iteration. Defaults to `fail`. enum: - fail - ignore onSkipped: type: string description: >- What a `skipped` status does to a gating iteration. Separate from `onError`: a crashed judge and a judge that never ran are different failures. enum: - fail - ignore model: type: string scope: type: object additionalProperties: true EvalFrictionSignal: type: object description: >- One observed pattern in a trial's tool calls. Identifier kinds carry `informationCallIndex` (where the identifiers appeared) and `observedAtCallIndex` (the later call that made the pattern visible); adjacency kinds carry `callIndex` and `priorCallIndex`. Every index addresses `actualToolCalls` on the same iteration. required: - kind - toolName properties: kind: type: string enum: - identifierSurfacedUnused - searchRepeatedAfterIdentifier - identicalRetry - changedRetry - paginationContinuation description: >- Which observable pattern this is. A CLOSED vocabulary; a reader that does not know a member must not guess at it. Every member has a benign reading, so none of them is a verdict about the trial. `identifierSurfacedUnused` — Identifiers surfaced, none used later: a result carried identifiers and no later call passed one, which is also what a search that already answered the question looks like. `searchRepeatedAfterIdentifier` — Same tool searched again after identifiers: the tool that surfaced them was called again with a different question, which is also what a sensible refinement looks like. `identicalRetry` — Repeated with identical arguments: the same call ran twice byte for byte, which is what recovery after a transient error looks like. `changedRetry` — Same tool called again with changed arguments: ordinary exploration, and most useful work looks like this. `paginationContinuation` — Pagination continued: only the pagination keys changed, which is a cursor doing its job and is never counted as a repeat. toolName: type: string toolCallId: type: string informationCallIndex: type: integer minimum: 0 observedAtCallIndex: type: integer minimum: 0 callIndex: type: integer minimum: 0 priorCallIndex: type: integer minimum: 0 afterError: type: boolean description: Whether the call this one repeats returned an error. identifierKeyPaths: type: array maxItems: 8 items: type: string description: >- Where in the result the identifiers were found (`results[].id`). KEY PATHS ONLY — an identifier VALUE never leaves the deployment. identifierCount: type: integer minimum: 1 laterCallCount: type: integer minimum: 2 repeatCallIndexes: type: array minItems: 1 maxItems: 8 items: type: integer minimum: 0 paginationKeys: type: array minItems: 1 maxItems: 4 items: type: string enum: - cursor - nextCursor - page - pageToken - offset - after - before - start - limit responses: Unauthorized: description: >- Missing, invalid, revoked, or orphaned key (`UNAUTHORIZED`) — or the **target MCP server** needs an OAuth grant (`OAUTH_REQUIRED`), which is a property of the server, not your key. content: application/json: schema: $ref: '#/components/schemas/Error' examples: badKey: summary: Invalid or revoked key value: code: UNAUTHORIZED message: Invalid API key oauthRequired: summary: Target server needs an OAuth grant value: code: OAUTH_REQUIRED message: Server requires OAuth authorization Forbidden: description: Key is valid but not allowed to do this. content: application/json: schema: $ref: '#/components/schemas/Error' example: code: FORBIDDEN message: You do not have access to this project NotFound: description: Unknown project, server, or resource. content: application/json: schema: $ref: '#/components/schemas/Error' example: code: NOT_FOUND message: Server not found RateLimited: description: >- Per-key rate limit exceeded (60 requests/minute sustained, bursts up to 10). Honor `Retry-After` and back off with jitter. headers: Retry-After: description: Seconds to wait before retrying. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' example: code: RATE_LIMITED message: API key rate limit exceeded. Slow down and retry. InternalError: description: Something failed on MCPJam's side. content: application/json: schema: $ref: '#/components/schemas/Error' example: code: INTERNAL_ERROR message: Unexpected internal error securitySchemes: bearerAuth: type: http scheme: bearer description: >- MCPJam API key (`sk_…`). Create one at [Settings → API keys](https://app.mcpjam.com/settings/api-keys). Guest sessions cannot use the API, and API keys cannot manage other API keys. ````