---
title: "Start a Claude directory-readiness run"
method: POST
path: "/projects/{projectId}/servers/{serverId}/readiness-runs/claude"
tags: ["Directory readiness"]
---

# Start a Claude directory-readiness run

`POST /projects/{projectId}/servers/{serverId}/readiness-runs/claude`

Grades the saved server against Anthropic's connector-directory requirements and returns `202` with a run id. The target comes from the saved server the path names: a body cannot supply a URL, an actor, an organization, a model or a cost. Poll the run detail for the verdict. Deterministic grading is free.

## Path parameters

- `projectId` string, required
- `serverId` string, required

## Request body

- object
  - `idempotencyKey` string — Deduplicates a retried POST. More load-bearing here than usual: a readiness run dials a third party's server, and a retried start that created a second run would do that twice.
  - `includeLlmObservations` boolean — Add model-backed experience observations. **Consumes MCPJam credits.** Off by default, and deliberately: a billed opt-in that defaulted on would start charging every existing caller on the day it shipped. Observations are non-dispositive and can never make a server not-ready; a refused reservation makes no provider call and completes the run with `llmObservations.reason` set to `billing_limit_reached`.

## Response `202`

The run was accepted and is executing.

- ReadinessRunReceipt — The 202 receipt. Poll the run detail; do not re-POST.
  - `runId` string, required
  - `projectId` string, required
  - `serverId` string, required
  - `readinessKind` 'claude' | 'openai', required
  - `status` 'pending' | 'running' | 'completed' | 'failed' | 'cancelled', required — The run's status when the start returned. `pending` for a fresh start; for a deduped start, whatever the existing run is already at — which may be `completed`, because a replayed idempotency key can name a run that finished long ago.
  - `deduped` boolean, required — This request replayed an existing run rather than starting one.
  - `includeLlmObservations` boolean, required

## Other responses

- `400` — The body carried an unknown key, or the server uses a transport no directory can list.
- `401` — 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.
- `403` — Key is valid but not allowed to do this.
- `404` — Unknown project, server, or resource.
- `429` — Per-key rate limit exceeded (60 requests/minute sustained, bursts up to 10). Honor `Retry-After` and back off with jitter.
- `500` — Something failed on MCPJam's side.

---

[API](https://skmtc.net/mcpjam/apis/mcpjam-api.md) · [All operations](https://skmtc.net/mcpjam/apis/mcpjam-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/mcpjam/mcpjam-api/revisions/8978a4e735fa/schema)