mcpField
T
Trigger.dev MCP by usefulapi

Trigger.dev MCP by usefulapi

Remote
usefulapi.ioDeveloper Tools0Updated today

About Trigger.dev MCP by usefulapi

Trigger.dev MCP by usefulapi is a hosted MCP server for developers working with Trigger.dev background jobs. It exposes run details and operational controls for investigating traces, schedules, queues and deployments without local installation.

Key features

  1. 01List runs and inspect run details
  2. 02View traces, spans, events and metadata
  3. 03Check batch results and schedules
  4. 04Inspect queues and current deployment
  5. 05Cancel, replay or reschedule runs
  6. 06Manage schedule and queue state

Use cases

  1. 01Trace a background run to investigate an issue
  2. 02Review run events and batch results
  3. 03Check schedules, queues or deployment state
  4. 04Cancel or replay a run during debugging

MCP support

It exposes Trigger.dev run, trace, schedule, queue and deployment data as MCP tools, along with write tools for run and operational controls. The hosted endpoint accepts Trigger.dev credentials through sign-in and stores them per user.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://trigger-dev.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

22
ParameterTypeRequiredDescription
tostringNoEpoch milliseconds upper bound on creation time.
tagarrayNoOnly runs carrying these tags.
fromstringNoEpoch milliseconds lower bound on creation time.
afterstringNoCursor from the previous page's pagination. Omit for the first page.
batchstringNoOnly runs in this batch.
queuearrayNoOnly runs on these queues.
isTestbooleanNoOnly test runs, or only real ones.
periodstringNoRelative window, e.g. "1h", "24h", "7d".
statusarrayNoOnly runs in these states, e.g. ["FAILED","CRASHED"]. Others include PENDING, EXECUTING, COMPLETED, CANCELED, TIMED_OUT.
machinearrayNoOnly runs on these machine presets.
versionstringNoOnly runs of this deployment version.
pageSizeintegerNoPage size, 1-100.
schedulestringNoOnly runs created by this schedule.
taskIdentifierarrayNoOnly runs of these task ids.

Details

From the project README

Trigger.dev MCP by usefulapi

Debug background jobs — runs, traces, spans, schedules, queues and deployments. Hosted, no local install.

Live endpoint: https://trigger-dev.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://trigger-dev.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http trigger-dev https://trigger-dev.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "trigger-dev": {
      "url": "https://trigger-dev.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Trigger.dev credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/trigger-dev/

On first connect you'll paste your Trigger.dev credentials. They are validated, stored per-user, and scoped to you — no keys in config files.

Tools

ToolTypeWhat it does
trigger_list_runsreadList runs
trigger_get_runreadGet one run
trigger_get_run_tracereadGet a run's trace
trigger_get_run_spanreadGet one span of a run
trigger_list_run_eventsreadList a run's events
trigger_get_run_metadatareadGet a run's metadata
trigger_get_batch_resultsreadGet a batch's results
trigger_list_schedulesreadList schedules
trigger_get_schedulereadGet one schedule
trigger_list_queuesreadList queues
trigger_get_queuereadGet one queue
trigger_get_current_deploymentreadGet the current deployment
trigger_list_env_varsreadList environment variables
trigger_list_waitpoint_tokensreadList waitpoint tokens
trigger_list_bulk_actionsreadList bulk actions
trigger_cancel_runwriteCancel a run
trigger_replay_runwriteReplay a run
trigger_reschedule_runwriteReschedule a delayed run
trigger_add_run_tagswriteAdd tags to a run
trigger_activate_schedulewriteActivate a schedule
trigger_deactivate_schedulewriteDeactivate a schedule
trigger_pause_queuewritePause or resume a queue
trigger_dev_usage_statusmetaUsage status (free-tier meter)
trigger_dev_request_featuremetaRequest a missing feature
trigger_dev_upgrademetaUpgrade to Pro (unlimited*)
trigger_dev_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with trigger_dev_upgrade (it returns a Stripe Checkout link). Cancel any time with trigger_dev_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running trigger_dev_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.