What is the Trigger.dev MCP Server?
The Trigger.dev MCP (Model Context Protocol) Server enables AI assistants to interact directly with your Trigger.dev projects. It provides a comprehensive set of tools to:- Search Trigger.dev documentation
- Initialize new Trigger.dev projects
- List and manage your projects and organizations
- Get task information and trigger task runs
- Deploy projects to different environments
- Monitor run details and list runs with filtering options
- Query your data with TRQL and run built-in dashboard metrics
Installation
The quickest way to get set up is the interactive installer:Client Configuration
Each client has a slightly different config format. Copy the snippet for your client into the appropriate file.- Claude Code
- Cursor
- Windsurf
- VS Code
- Zed
- Cline
- Gemini CLI
- AMP
- Codex CLI
- Crush
- opencode
- Ruler
Install using the command line:Or add this configuration to View Claude Code MCP docs ↗
~/.claude.json (user) or .mcp.json (project):Authentication
Thesearch_docs tool works without authentication, and so do the local-only tools list_profiles, dev_server_status and stop_dev_server. All other tools require you to be logged in via the Trigger.dev CLI. The first time you use an authenticated tool, your MCP client will prompt you to log in.
CLI Options
CLI Options
The Install for specific clients:Restrict to dev environment for a specific project:To add these options to a manual config, append them to the The
install-mcp command supports these options:Core Options-p, --project-ref <project ref>— Scope the MCP server to a specific project-t, --tag <package tag>— CLI package version to use (default: latest)--dev-only— Restrict to the dev environment only--yolo— Install into all supported clients automatically--scope <scope>—user,project, orlocal--client <clients...>— Install into specific client(s)
--log-file <log file>— Write logs to a file-a, --api-url <value>— Custom Trigger.dev API URL-l, --log-level <level>— Log level (debug, info, log, warn, error, none)
args array:mcp command also accepts --readonly, which hides the tools that write to your account (for example deploy, trigger_task and cancel_run) so the AI cannot make changes to it. It is only available as a manual config arg:Getting Started
Once installed, you can start using the MCP server by asking your AI assistant questions like:"Search the trigger docs for a ffmpeg example""Initialize trigger.dev in my project""Get all tasks in my project""Trigger my foobar task with a sample payload""Get the details of the latest run for my foobar task""List all runs for my foobar task""Deploy my project to staging""Deploy my project to production""How many runs failed in the last 7 days?""Show me the overview dashboard metrics""What tables can I query?"
Next Steps
MCP Tools
Explore all available MCP tools for managing your projects.
Skills
Portable instruction sets that teach AI assistants Trigger.dev patterns.

