---
title: "Launch a journey"
method: POST
path: "/projects/{projectId}/journeys/{journeyId}/runs"
tags: ["Swarm runs"]
---

# Launch a journey

`POST /projects/{projectId}/journeys/{journeyId}/runs`

Answers **202**: the run row exists and its fan-out has started. It is not finished — poll `GET /projects/{projectId}/journey-runs/{runId}` until `status` leaves `running`.

**SPENDS.** A launch fans out into `targets × sessionsPerTarget` chat sessions, every one of which runs a model on your organization's account.

Two different 429s can come back and they mean different waits: the per-minute burst brake (retry in seconds) and your plan's daily launch cap (resets at UTC midnight). Both normally carry `Retry-After` — honor it when it is there, and back off on your own when it is not, rather than blocking on a header that may not come. A retried `Idempotency-Key` consumes NO quota.

## Headers

- `Idempotency-Key` string

## Request body

- JourneyRunLaunchRequest — Optional. A launch with no options is a BODYLESS POST — omit the body entirely rather than sending `null`, which is rejected.
  - `waveId` string — Opaque id linking the sibling runs of one co-launched batch. Mint it yourself and reuse it across the launches you want grouped.
  - `environmentIds` string[] — Fan out across THESE environments instead of the journey's authored targets. NON-EMPTY when present: `[]` is a caller saying "across these" while naming none, and would have silently launched the authored targets instead. Silently running something other than what was asked for is bad anywhere; on an operation that spends it is worse. Omit the field to mean "as authored".

## Response `202`

The run was accepted and started.

- JourneyRunLaunched
  - `id` string, required — The run id. Poll it, or stop it with `cancel`.
  - `journeyId` string, required
  - `projectId` string, required
  - `status` 'running', required — Always `running` — the run row exists and its fan-out has started. This is a 202: nothing here says the journey has finished, only that it is under way.
  - `deduped` boolean, required — True when an `Idempotency-Key` replayed onto a run that ALREADY existed, so nothing new was started. The response is otherwise identical, which is how a retry of a dropped request tells "I launched it" from "it was already going" without a second read.

## Other responses

- `400` — Malformed body or parameters.
- `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.
- `409` — The resource is not in a state that accepts this write — a stale `expectedRevision`, a duplicate name, or an environment that cannot currently be launched. The request was well-formed; re-read the resource and retry.
- `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/8bf151c2dd8b/schema)