Trigger.dev MCP server. Debug background jobs — runs, traces, spans, schedules, queues and deployments.
Add to your MCP config, then reload & authorize:
{
"mcpServers": {
"trigger-dev": {
"url": "https://trigger-dev.usefulapi.io/mcp"
}
}
}| Tool | Type | What it does |
|---|---|---|
trigger_list_runs | read | List runs List task runs, filtered by status, task, tag, queue, schedule or a time window. This is the main read for 'what ran, and what failed?'. Trigger.dev: GET /api/v1/runs. |
trigger_get_run | read | Get one run Fetch a single run's outcome — its status, output, error and attempts. Trigger.dev: GET /api/v1/runs/{runId}/result. |
trigger_get_run_trace | read | Get a run's trace Fetch the full execution trace of a run — every span, with timings and nesting. The tool for 'where did this run spend its time, and where did it break?'. Trigger.dev: GET /api/v1/runs/{runId}/trace. |
trigger_get_run_span | read | Get one span of a run Fetch a single span from a run's trace, with its own logs and attributes. Trigger.dev: GET /api/v1/runs/{runId}/spans/{spanId}. |
trigger_list_run_events | read | List a run's events List the lifecycle events of one run — queued, dequeued, started, retried, completed. Trigger.dev: GET /api/v1/runs/{runId}/events. |
trigger_get_run_metadata | read | Get a run's metadata Fetch the mutable metadata a run has written about itself — progress, checkpoints and custom state. Trigger.dev: GET /api/v1/runs/{runId}/metadata. |
trigger_get_batch_results | read | Get a batch's results Fetch the outcome of every run in a batch. Trigger.dev: GET /api/v1/batches/{batchId}/results. |
trigger_list_schedules | read | List schedules List the cron schedules configured for tasks, with their next run times. Trigger.dev: GET /api/v1/schedules. |
trigger_get_schedule | read | Get one schedule Fetch a single schedule with its cron expression, timezone and active state. Trigger.dev: GET /api/v1/schedules/{scheduleId}. |
trigger_list_queues | read | List queues List task queues with their concurrency limits and current depth — where you look when work is backing up. Trigger.dev: GET /api/v1/queues. |
trigger_get_queue | read | Get one queue Fetch a single queue's concurrency limit, running count and queued count. Trigger.dev: GET /api/v1/queues/{queue}. |
trigger_get_current_deployment | read | Get the current deployment Fetch the deployment currently serving the key's environment — its version, git ref and status. Trigger.dev: GET /api/v1/deployments/current. |
trigger_list_env_vars | read | List environment variables List the environment variables configured for a project environment. Values may be redacted depending on the key's permissions. READ ONLY — this server exposes no env-var writes. Trigger.dev: GET /api/v1/projects/{projectRef}/envvars/{env}. |
trigger_list_waitpoint_tokens | read | List waitpoint tokens List outstanding waitpoint tokens — runs paused waiting for an external signal. Trigger.dev: GET /api/v1/waitpoints/tokens. |
trigger_list_bulk_actions | read | List bulk actions List bulk replay and cancel operations and their progress. Trigger.dev: GET /api/v1/bulk-actions. |
trigger_cancel_run | write | Cancel a run Cancel an in-flight run. Note this is the one endpoint on API v2, not v1. Trigger.dev: POST /api/v2/runs/{runId}/cancel. |
trigger_replay_run | write | Replay a run Re-run one specific past run with the same payload. This EXECUTES your production task again — the same side effects it had the first time. Trigger.dev: POST /api/v1/runs/{runId}/replay. |
trigger_reschedule_run | write | Reschedule a delayed run Change when a delayed run will execute. Only applies to runs that have not started. Trigger.dev: POST /api/v1/runs/{runId}/reschedule. |
trigger_add_run_tags | write | Add tags to a run Attach tags to a run so you can filter for it later. Additive and safe. Trigger.dev: POST /api/v1/runs/{runId}/tags. |
trigger_activate_schedule | write | Activate a schedule Resume a paused schedule so it fires again. Trigger.dev: POST /api/v1/schedules/{scheduleId}/activate. |
trigger_deactivate_schedule | write | Deactivate a schedule Pause a schedule so it stops firing. The usual first move when a scheduled task is misbehaving. Trigger.dev: POST /api/v1/schedules/{scheduleId}/deactivate. |
trigger_pause_queue | write | Pause or resume a queue Pause a queue so its runs stop being dequeued, or resume it. The containment move when a task is failing in a loop. Trigger.dev: POST /api/v1/queues/{queue}/pause. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.