Application Development
Inngest MCP connector
The Inngest connector lets Claude, ChatGPT, Cursor and other MCP clients list your Inngest apps, functions, runs and environments, rerun or invoke functions, and manage webhooks and keys, with every action signed in as you and logged.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Inngest to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Inngest once
-
Open Connections, choose Add connection, and pick Inngest.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste an Inngest API key. One person generates a token in Inngest and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Inngest to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Inngest to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Inngest to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Inngest to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Inngest through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Find out why a run failed
Ask for the failed runs of a function from the last hour and pull up one run to see where it stopped and what it was working on.
-
On-call
Rerun the jobs that failed overnight
List the runs that failed while nobody was watching, then rerun them in one go once the cause is fixed.
-
Engineering
Trigger a function on demand
Invoke a function with the payload you need to test a fix or process one customer's data right now, without opening the Inngest dashboard.
-
Platform
Set up a new environment with webhooks
Create a staging or preview environment, add the webhooks it needs and confirm which event keys and signing keys belong to it.
-
Support
Check whether a customer's job ran
When a customer says an email or export never arrived, look up the event runs for that event and see whether the function ran, is still running or failed.
-
Product
Review function experiments and score runs
List the experiments running on a function, compare their runs and record a score against a run so the team can see which version is winning.
Try asking
- “List failed event runs for our checkout functions this week.”
- “Which Inngest apps have functions without a recent sync?”
- “Show function experiments running in the production env.”
AI tools
Inngest tools for your AI agents
39 tools are ready to call through Elaichi's MCP endpoint the moment you connect Inngest, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Inngest gets you
6 screens from the product, each doing one job for your Inngest account.
The agent
Ask about Inngest runs, get answers.
Plain language questions answered from live Inngest apps, functions and event runs.
- apps
- functions
- event runs
- webhooks
Ask Elaichi to work across your apps.
List failed event runs for our checkout functions this week.
Which Inngest apps have functions without a recent sync?
Show function experiments running in the production env.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Inngest.
One governed MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
39 Inngest tools ready without custom code.
Browse apps, functions, experiments, envs and webhooks with methods already wired up.
- List all Inngest accounts
- Get single Inngest app by ID
- List all Inngest app functions
- Get single Inngest app function by ID
Toolboxes
Every team gets its own Inngest toolbox.
Platform, backend and on call each see the Inngest tools they need.
- Platform
- Backend
- On call
- Integrations
Shared connections
Teammates run Inngest without a credential.
See who connected each Inngest account and which teams and members use it.
- Production
- Staging
- Platform
- Payments
Audit log
Every Inngest call is on the record.
When, who, what happened, type and resource for each Inngest function and run.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires, Inngest work gets done.
Fetch event runs, group them, draft a digest, approve, post back to Inngest.
Inngest digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch apps
Inngest
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Inngest
Queued
Collections and dashboards
Inngest health, counted on a schedule.
Four metrics, 14 days of runs created and a breakdown by team.
Inngest health
Refreshed 4 minutes ago · every 15 minutes · from the apps collection
Apps
1,284 ↓ 12%
Functions
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Apps created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
Platform 21%
Payments 18%
FAQ
Frequently asked questions
How do I connect Inngest to Claude?
Connect Inngest in Elaichi by pasting an API key from your Inngest account; there is no OAuth app to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and Inngest is available in your chat.
Does Inngest work with ChatGPT and Cursor as well as Claude?
Yes. Once Inngest is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Inngest once and every client picks it up.
What can an AI agent actually do with my Inngest data?
With Inngest connected, an agent can list your apps, functions, environments, runs and event runs, open a single run to see what happened, rerun or delete a run, invoke a function, sync an app after a deploy, create or update environments, add webhooks and check event keys and signing keys. Because Inngest exposes many actions, short concrete asks such as "show failed runs for the billing function today" work better than long sentences.
Does connecting Inngest give the AI access to every environment and account?
No. Every request to Inngest runs under the API key of the person who connected it, so the agent can only see the accounts, environments and functions that key already reaches in Inngest. Elaichi can narrow that further with restrictions per action, and it can never widen it beyond what Inngest itself allows.
Can I stop an agent from deleting or changing things in Inngest?
Yes. Restrictions in Elaichi work per action, so you can allow reading Inngest runs and functions while blocking deleting a run, invoking a function or changing an environment. A blocked action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can reach it.
What happens to an Inngest connection when someone leaves?
When you offboard a person in Elaichi, their access to Inngest through every client ends at once. If they shared an Inngest connection, it keeps working for everyone else on the team. Disconnecting Inngest once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.
Put Inngest in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.