Inngest for background jobs
Inngest's official Dev Server MCP is our second pick for background jobs, and it fits the event-driven shape well: an agent can fire an event, invoke a function, and watch the run, against a model that comes with built-in retries and step functions. Both starting work and reasoning about whether it succeeded happen through the same tools.
It ranks second of four because it targets the local Inngest dev server, so it is strongest in development and testing rather than as a production control plane. Temporal, Trigger.dev, and Windmill each fit a different execution model, and one of them may suit a given setup better.
How Inngest fits
The trigger-and-observe loop runs through four tools. send_event fires an event and reports immediately which runs it created, invoke_function executes a function directly and waits for its result, and list_functions discovers what is registered with its trigger info. For observation, get_run_status returns detailed status and step-by-step trace for one run, and poll_run_status monitors several runs until they finish, which the server itself calls out as useful for integration testing. The documentation tools, grep_docs, read_doc, and list_docs, let the agent look up Inngest behavior without leaving the session.
The honest limit is the dev-server scope: this connects to your local Inngest dev server, so it is built for development and integration testing more than driving production jobs. Temporal is the stronger pick when you need durable workflows that survive process crashes; Trigger.dev fits a developer-friendly job runner you operate; Windmill suits a scriptable runner across languages. Reach for Inngest when your background work is event-driven with retries and step functions and you want an agent triggering and inspecting runs against the dev server.
Tools you would use
| Tool | What it does |
|---|---|
| send_event | Send an event to trigger functions and get immediate feedback on which runs were created. |
| list_functions | Discover all registered functions with their names, IDs, and event-trigger information. |
| invoke_function | Directly execute a function and wait for its complete result. |
| get_run_status | Get detailed status and trace information for a specific function run, including step-by-step execution details. |
| poll_run_status | Monitor multiple function runs until they complete — useful for integration testing. |
| grep_docs | Search the embedded Inngest documentation using pattern matching. |
| read_doc | Read the complete content of a specific documentation file. |
| list_docs | Get an overview of all available documentation with a category breakdown. |
FAQ
- Can the Inngest MCP server trigger a job and confirm it finished?
- Yes. send_event or invoke_function starts the work, and get_run_status or poll_run_status tracks it to completion, including step-by-step trace detail. poll_run_status is noted as useful for integration testing across multiple runs.
- Does the Inngest server work against production or only the dev server?
- It is the Dev Server MCP, scoped to your local Inngest dev server, so it is strongest for development and integration testing. For durable production workflows, Temporal is the stronger pick among the options here.