# io.usefulapi/trigger-dev (remote · trigger-dev.usefulapi.io)

Debug background jobs — runs, traces, spans, schedules, queues and deployments.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- remote · `trigger-dev.usefulapi.io`: 78/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev.md), [page](https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev)

## Channel facts

- Endpoint: `https://trigger-dev.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-04.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1594 tokens (~72/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.usefulapi/trigger-dev MCP server?

io.usefulapi/trigger-dev is a hosted endpoint at https://trigger-dev.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.io-usefulapi-trigger-dev]
url = "https://trigger-dev.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-trigger-dev": {
      "type": "remote",
      "url": "https://trigger-dev.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-trigger-dev --url 'https://trigger-dev.usefulapi.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-trigger-dev:
    url: "https://trigger-dev.usefulapi.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-usefulapi-trigger-dev": {
      "Transport": "http",
      "Url": "https://trigger-dev.usefulapi.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-usefulapi-trigger-dev -t streamable-http -u 'https://trigger-dev.usefulapi.io/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-04 (score 78, +60)

- [security improvement] HTTPS: unverified → pass
- [security improvement] Authorization: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.07

### 2026-10-03 (score 18, −59)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] HTTPS: pass → unverified
- [security regression] Authorization: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-02 (score 77, +59)

- [security improvement] HTTPS: unverified → pass
- [security improvement] Authorization: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [security] First check of Authorization: partial
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-09-29 (score 18)

First indexed and scored.

## MCP tools (22)

### `trigger_list_runs` (~290 tokens)

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.

Input parameters:

- `after` (string): Cursor from the previous page's pagination. Omit for the first page.
- `batch` (string): Only runs in this batch.
- `from` (string): Epoch milliseconds lower bound on creation time.
- `isTest` (boolean): Only test runs, or only real ones.
- `machine` (array): Only runs on these machine presets.
- `pageSize` (integer): Page size, 1-100.
- `period` (string): Relative window, e.g. "1h", "24h", "7d".
- `queue` (array): Only runs on these queues.
- `schedule` (string): Only runs created by this schedule.
- `status` (array): Only runs in these states, e.g. ["FAILED","CRASHED"]. Others include PENDING, EXECUTING, COMPLETED, CANCELED, TIMED_OUT.
- `tag` (array): Only runs carrying these tags.
- `taskIdentifier` (array): Only runs of these task ids.
- `to` (string): Epoch milliseconds upper bound on creation time.
- `version` (string): Only runs of this deployment version.

### `trigger_get_run` (~57 tokens)

Get one run

Fetch a single run's outcome — its status, output, error and attempts. Trigger.dev: GET /api/v1/runs/{runId}/result.

Input parameters:

- `run_id` (string, required): The run's id (run_...).

### `trigger_get_run_trace` (~74 tokens)

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.

Input parameters:

- `run_id` (string, required): The run's id.

### `trigger_get_run_span` (~75 tokens)

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}.

Input parameters:

- `run_id` (string, required): The run's id.
- `span_id` (string, required): The span's id, from the trace.

### `trigger_list_run_events` (~58 tokens)

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.

Input parameters:

- `run_id` (string, required): The run's id.

### `trigger_get_run_metadata` (~56 tokens)

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.

Input parameters:

- `run_id` (string, required): The run's id.

### `trigger_get_batch_results` (~52 tokens)

Get a batch's results

Fetch the outcome of every run in a batch. Trigger.dev: GET /api/v1/batches/{batchId}/results.

Input parameters:

- `batch_id` (string, required): The batch's id (batch_...).

### `trigger_list_schedules` (~62 tokens)

List schedules

List the cron schedules configured for tasks, with their next run times. Trigger.dev: GET /api/v1/schedules.

Input parameters:

- `page` (integer): 1-based page number.
- `pageSize` (integer): Page size, 1-100.

### `trigger_get_schedule` (~53 tokens)

Get one schedule

Fetch a single schedule with its cron expression, timezone and active state. Trigger.dev: GET /api/v1/schedules/{scheduleId}.

Input parameters:

- `schedule_id` (string, required): The schedule's id (sched_...).

### `trigger_list_queues` (~56 tokens)

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.

Input parameters:

- `pageSize` (integer): Page size, 1-100.

### `trigger_get_queue` (~49 tokens)

Get one queue

Fetch a single queue's concurrency limit, running count and queued count. Trigger.dev: GET /api/v1/queues/{queue}.

Input parameters:

- `queue` (string, required): The queue's name or id.

### `trigger_get_current_deployment` (~42 tokens)

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` (~89 tokens)

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}.

Input parameters:

- `environment` (string, required): Which environment's variables to list.
- `project_ref` (string, required): The project reference (proj_...).

### `trigger_list_waitpoint_tokens` (~75 tokens)

List waitpoint tokens

List outstanding waitpoint tokens — runs paused waiting for an external signal. Trigger.dev: GET /api/v1/waitpoints/tokens.

Input parameters:

- `after` (string): Cursor from the previous page's pagination. Omit for the first page.
- `pageSize` (integer): Page size, 1-100.

### `trigger_list_bulk_actions` (~47 tokens)

List bulk actions

List bulk replay and cancel operations and their progress. Trigger.dev: GET /api/v1/bulk-actions.

Input parameters:

- `pageSize` (integer): Page size, 1-100.

### `trigger_cancel_run` (~58 tokens)

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.

Input parameters:

- `run_id` (string, required): The run to cancel.

### `trigger_replay_run` (~68 tokens)

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.

Input parameters:

- `run_id` (string, required): The run to replay.

### `trigger_reschedule_run` (~83 tokens)

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.

Input parameters:

- `delay` (string, required): New delay or timestamp, e.g. "1h" or an ISO-8601 datetime.
- `run_id` (string, required): The delayed run to move.

### `trigger_add_run_tags` (~66 tokens)

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.

Input parameters:

- `run_id` (string, required): The run to tag.
- `tags` (array, required): Tags to add.

### `trigger_activate_schedule` (~46 tokens)

Activate a schedule

Resume a paused schedule so it fires again. Trigger.dev: POST /api/v1/schedules/{scheduleId}/activate.

Input parameters:

- `schedule_id` (string, required): The schedule to activate.

### `trigger_deactivate_schedule` (~60 tokens)

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.

Input parameters:

- `schedule_id` (string, required): The schedule to pause.

### `trigger_pause_queue` (~78 tokens)

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.

Input parameters:

- `paused` (boolean, required): true to pause, false to resume.
- `queue` (string, required): The queue's name or id.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev#diagnostics

## Score history

- 2026-10-04: 78
- 2026-10-03: 18
- 2026-10-02: 77
- 2026-10-01: 18
- 2026-09-30: 18
- 2026-09-29: 18

## Common questions

### What is the io.usefulapi/trigger-dev MCP server?

io.usefulapi/trigger-dev is an MCP server listed in the public MCP registry as io.usefulapi/trigger-dev. Debug background jobs, runs, traces, spans, schedules, queues and deployments. This page covers its hosted endpoint (https://trigger-dev.usefulapi.io/mcp).

### Is the io.usefulapi/trigger-dev MCP server safe to use?

io.usefulapi/trigger-dev scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.usefulapi/trigger-dev MCP server expose?

io.usefulapi/trigger-dev exposes 22 tools: trigger_list_runs, trigger_get_run, trigger_get_run_trace, trigger_get_run_span, trigger_list_run_events, and 17 more. Their descriptions and schemas cost roughly 1,594 tokens of context every time the server is loaded.

### Does the io.usefulapi/trigger-dev MCP server require authentication?

Yes. io.usefulapi/trigger-dev asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the io.usefulapi/trigger-dev MCP server still maintained?

io.usefulapi/trigger-dev is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://trigger-dev.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-trigger-dev/trigger-dev