Trigger.dev MCP server

Debug background jobs — runs, traces, spans, schedules, queues and deployments. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.

Connect Trigger.devFree 50 tool calls / monthPro $9/mo · $90/yr · pricing26 tools

What can I ask?

Turn on the Trigger.dev connector, then ask in plain words. The AI picks the tools.

What you can do with Trigger.dev in Claude and ChatGPT

For developers who run background tasks on Trigger.dev.

Find failed runs and read their errors

The AI lists runs filtered by status, task, tag, queue or time window, then opens a run to read its output, error and attempts.

Find where a run spent its time or broke

The AI reads the full trace of a run with every span and its timing, one span with its logs, and the lifecycle events (queued, started, retried, completed).

Check queues that are backing up

The AI lists queues with their concurrency limit, running count and queued count, so you see where work piles up.

Review cron schedules and their next runs

The AI lists schedules with cron expression, timezone, active state and next run times.

Pause or resume a schedule or a queue

The AI deactivates a schedule that misbehaves, activates it again later, or pauses a queue so its runs stop being dequeued.

Changes data

Cancel, replay, reschedule or tag a run

The AI cancels a run in flight, replays a past run with the same payload, changes the time of a delayed run, or adds tags to a run.

Changes data

How do I connect Trigger.dev?

Before you connect

The login page asks for your Trigger.dev secret key.

Copy it from your Trigger.dev project's API keys page. Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.

Claude claude.ai · Desktop

  1. Open Customize → Connectors, then click + Add → Add custom connector.
  2. Enter the name Trigger.dev and this URL, then click Add:
    https://trigger-dev.usefulapi.io/mcp
  3. Claude opens the login page: enter your Trigger.dev secret key.
  4. In a chat, click + → Connectors and turn on Trigger.dev.

Team and Enterprise: an Owner adds the connector for the organization first.

ChatGPT chatgpt.com

  1. Open Plugins, click +, then Add custom MCP server.
  2. Enter the name Trigger.dev and this URL, choose OAuth as the authentication, confirm the warning and create it:
    https://trigger-dev.usefulapi.io/mcp
  3. ChatGPT opens the login page: enter your Trigger.dev secret key.
  4. In Plugins, install Trigger.dev, then choose it in a chat.

No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.

Claude Code

Run this command, then run /mcp in Claude Code to log in:

claude mcp add --transport http trigger-dev https://trigger-dev.usefulapi.io/mcp

Cursor

Add to Cursor or add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "trigger-dev": {
      "url": "https://trigger-dev.usefulapi.io/mcp"
    }
  }
}

VS Code

Add to VS Code or add this to .vscode/mcp.json:

{
  "servers": {
    "trigger-dev": {
      "type": "http",
      "url": "https://trigger-dev.usefulapi.io/mcp"
    }
  }
}

Codex

Run these commands. The second one opens the login page:

codex mcp add trigger-dev --url https://trigger-dev.usefulapi.io/mcp
codex mcp login trigger-dev

Other clients

Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.

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: the login page asks for your Trigger.dev secret key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo · $90/yr10,000 tool calls / month
Pro+$39/mo · $390/yr100,000 tool calls / month

Each paid plan covers this Trigger.dev server only. Ask your AI to run trigger_dev_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with trigger_dev_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with trigger_dev_upgrade before then undoes the cancel. Or write to [email protected].

Tools 26

Show all 26 tools (the AI picks them for you)

Read only · 15

  • List runstrigger_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?'.
  • Get one runtrigger_get_run
    Fetch a single run's outcome — its status, output, error and attempts.
  • Get a run's tracetrigger_get_run_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?'.
  • Get one span of a runtrigger_get_run_span
    Fetch a single span from a run's trace, with its own logs and attributes.
  • List a run's eventstrigger_list_run_events
    List the lifecycle events of one run — queued, dequeued, started, retried, completed.
  • Get a run's metadatatrigger_get_run_metadata
    Fetch the mutable metadata a run has written about itself — progress, checkpoints and custom state.
  • Get a batch's resultstrigger_get_batch_results
    Fetch the outcome of every run in a batch.
  • List schedulestrigger_list_schedules
    List the cron schedules configured for tasks, with their next run times.
  • Get one scheduletrigger_get_schedule
    Fetch a single schedule with its cron expression, timezone and active state.
  • List queuestrigger_list_queues
    List task queues with their concurrency limits and current depth — where you look when work is backing up.
  • Get one queuetrigger_get_queue
    Fetch a single queue's concurrency limit, running count and queued count.
  • Get the current deploymenttrigger_get_current_deployment
    Fetch the deployment currently serving the key's environment — its version, git ref and status.
  • List environment variablestrigger_list_env_vars
    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.
  • List waitpoint tokenstrigger_list_waitpoint_tokens
    List outstanding waitpoint tokens — runs paused waiting for an external signal.
  • List bulk actionstrigger_list_bulk_actions
    List bulk replay and cancel operations and their progress.

Changes data · 7

  • Cancel a runtrigger_cancel_run
    Cancel an in-flight run. Note this is the one endpoint on API v2, not v1.
  • Replay a runtrigger_replay_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.
  • Reschedule a delayed runtrigger_reschedule_run
    Change when a delayed run will execute. Only applies to runs that have not started.
  • Add tags to a runtrigger_add_run_tags
    Attach tags to a run so you can filter for it later. Additive and safe.
  • Activate a scheduletrigger_activate_schedule
    Resume a paused schedule so it fires again.
  • Deactivate a scheduletrigger_deactivate_schedule
    Pause a schedule so it stops firing. The usual first move when a scheduled task is misbehaving.
  • Pause or resume a queuetrigger_pause_queue
    Pause a queue so its runs stop being dequeued, or resume it. The containment move when a task is failing in a loop.

Your usefulapi plan · 4

  • Usage status (free-tier meter)trigger_dev_usage_status
    Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter.
  • Request a missing featuretrigger_dev_request_feature
    Tell usefulapi that the user needs something the Trigger.dev tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter.
  • Upgrade to Pro or Pro+trigger_dev_upgrade
    Get a paid plan for Trigger.dev (the free tier caps monthly usage). Pro: 10,000 tool calls a month, for normal use — plan "monthly" ($9/month) or "yearly" ($90/year, 2 months free). Pro+: 100,000 tool calls a month, for automations and heavy use — plan "plus" ($39/month) or "plus_yearly" ($390/year). Without a plan it returns both Pro and Pro+, each with a payment link, for the user to choose; with a plan, one link. An existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Cancel any time: the plan then runs to the end of the paid period, so it also suits a one-time job. A link opens Stripe Checkout in the browser; after payment the account upgrades automatically. Does not count against the meter.
  • Cancel the Pro subscriptiontrigger_dev_cancel_subscription
    Cancel the caller's Trigger.dev Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run trigger_dev_upgrade later to undo the cancel before the period ends. Does not count against the meter.

FAQ

What can I do with Trigger.dev in Claude or ChatGPT?

Find failed runs and read their errors. Find where a run spent its time or broke. Check queues that are backing up. Review cron schedules and their next runs. Pause or resume a schedule or a queue. Cancel, replay, reschedule or tag a run. See what you can do for the details.

Is this an official Trigger.dev product?

No. usefulapi is an independent service. It is not affiliated with or endorsed by Trigger.dev. The server calls the Trigger.dev API with your own Trigger.dev access, so it sees only the data that your account can see.

Can I connect Trigger.dev to Claude or ChatGPT?

Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.

What do I need to connect?

The login page asks for your Trigger.dev secret key. See Before you connect for where to find it.

Do I put my Trigger.dev key or an Authorization header in the client config?

No. 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: the login page asks for your Trigger.dev secret key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.

How do you keep my Trigger.dev credentials?

The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Trigger.dev API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Trigger.dev.

Can the AI change my Trigger.dev data?

Yes, if you approve it. 7 of the 22 Trigger.dev tools can create or change data. The other 15 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.

What does it cost?

The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this Trigger.dev server only. Cancel any time: your paid plan then runs to the end of the paid period. Run trigger_dev_usage_status to see how many calls you used.

How do I subscribe or cancel?

Ask the AI to run trigger_dev_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run trigger_dev_cancel_subscription. Your paid plan continues to the end of the paid period.

What if a Trigger.dev tool that I need is missing?

Tell the AI what you wanted to do. It can send the request with trigger_dev_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.

Which AI clients can I use?

Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.

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.

Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.

More Developer Tools & Infrastructure MCP servers

AblyAction1ApiFlashbunny.netButterCMSCaisyCivoClouDNSCodecovCodemagicComet BackupCrowdinDepotdeSECDNSimpleDubEstuary FlowExoscaleGandiGeoapifyHetzner CloudHexnodeHypertuneInngestINWXipapi.isKindeKinstaKisiKnackLaravel ForgeLingoHubLocalazyMapTilerNorthflankNS1 ConnectpackagecloudPlay SystemsQuickbaseRealtime RegisterRelease RadarRunCloudScalefusionScalingoSpinupWPSvixTailscaleTreePlotterUnkeyUpCloudWakaTimeWeblate

All Developer Tools & Infrastructure servers →