Skip to content
Trigger.dev MCP Server

Trigger.dev MCP Server

by Trigger.dev
Added to Onei
Apache-2.0
Repository Docs npm
Developer Tools

Summary

Trigger.dev's official MCP server — trigger and monitor background jobs, deploy to any environment, and query runs with TRQL from your coding agent.

Features

  • Trigger tasks and wait for runs to complete
  • Monitor, list and cancel runs
  • Deploy to preview and production environments
  • Query runs and dashboards with TRQL
  • Start and stop the local dev server
  • Documentation search with no authentication
  • --readonly and --dev-only flags to restrict write access
  • One-command setup via npx trigger.dev install-mcp

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Trigger.dev MCP Server" tools will be available.
{
  "mcpServers": {
    "trigger-dev-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "trigger.dev@latest",
        "mcp"
      ]
    }
  }
}

Description

The Trigger.dev MCP Server is the official Model Context Protocol integration for Trigger.dev, the open-source background-jobs platform. It gives a coding agent the same reach over your tasks, runs and deployments that the dashboard and CLI have.

Tools across ten areas. Documentation search (search_docs); organisations and projects (list_orgs, list_projects, create_project_in_org, initialize_project); task execution (get_current_worker, trigger_task); run monitoring (list_runs, get_run_details, wait_for_run_to_complete, cancel_run); deployment (deploy, list_deploys, list_preview_branches); profiles (whoami, list_profiles, switch_profile); analytics via TRQL (get_query_schema, query, list_dashboards, run_dashboard_query); local dev-server control (start_dev_server, stop_dev_server, dev_server_status); agent chat; and session channels.

The parts that matter in practice. wait_for_run_to_complete lets an agent trigger a job and block on the result instead of polling, which is what makes it usable inside a build-and-verify loop. start_dev_server means the agent can bring the local Trigger.dev dev server up itself rather than asking you to open another terminal. And query exposes TRQL, Trigger.dev's own run query language, so an agent can answer "which tasks failed most often this week" rather than paging through runs.

Guardrails for handing an agent deploy access. Two CLI flags narrow what the server will do: --readonly blocks every write — deploys, task triggering, run cancellation and agent chat — and --dev-only blocks deployment and preview-branch tools while leaving local development intact. search_docs needs no authentication at all, so documentation lookups work before you have connected anything.

Setup. npx trigger.dev@latest install-mcp configures it automatically; the docs carry explicit config for 15+ clients including Claude Code, Cursor, VS Code, Zed and Cline. Apache-2.0 licensed.

Related MCP Servers

MCP: Engram

by Gentleman Programming

New

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

Developer Tools
1 views

MCP: agent-device

by Callstack

New

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

Developer Tools
1 views

MCP: Weights & Biases MCP Server

by Weights & Biases

New

The official W&B MCP server: query experiment runs, Weave LLM traces, artifacts and registries in natural language, and write findings back as a W&B report.

Developer Tools
3 views

MCP: Replicate MCP Server

by Replicate

New

Replicate's official MCP server: search thousands of hosted models, read their schemas, and run predictions on image, video, audio and language models from inside an agent.

Developer Tools
2 views
Browse all MCP servers →