Application Development
Apache Airflow MCP connector
The Apache Airflow connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent manage Apache Airflow users, roles, and permissions through one governed endpoint, with every change running as the signed-in person and recorded in an audit log.
-
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.
11 tools
How to connect
How to connect Apache Airflow to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Apache Airflow once
-
Open Connections, choose Add connection, and pick Apache Airflow.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste an Apache Airflow API key. One person generates a token in Apache Airflow 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 Apache Airflow 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 Apache Airflow 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 Apache Airflow 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 Apache Airflow 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 Apache Airflow through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Data Engineering
Onboard a new engineer to Airflow
Create the Apache Airflow account for a new hire and attach the right role in one request, instead of clicking through the admin screens.
-
IT
Find out who still has access
Ask for the full list of Apache Airflow users and see at a glance which accounts belong to people who have moved teams or left.
-
Security
Review what a role can do
Pull up any Apache Airflow role, check the permissions behind it, and compare it against what the team actually needs.
-
Platform
Build a role for a new team
Create an Apache Airflow role scoped to what the analytics team needs, then adjust it as the team's work changes.
-
Compliance
Answer an access audit in minutes
List every Apache Airflow user, their roles, and the permissions those roles carry, ready to paste into an access review.
-
IT
Clean up a departed user's account
Look up the Apache Airflow user by ID, confirm the details, and remove the account when someone leaves the organization.
Try asking
- “List all Apache Airflow users and their assigned roles.”
- “Which Apache Airflow roles carry write permissions?”
- “Create an Apache Airflow user on the Viewer role.”
AI tools
Apache Airflow tools for your AI agents
11 tools are ready to call through Elaichi's MCP endpoint the moment you connect Apache Airflow, 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 Apache Airflow gets you
6 screens from the product, each doing one job for your Apache Airflow account.
The agent
Ask about Apache Airflow users in plain language.
Starter prompts return answers from live Apache Airflow users, roles and permissions.
- users
- roles
- permissions
- resources
Ask Elaichi to work across your apps.
List all Apache Airflow users and their assigned roles.
Which Apache Airflow roles carry write permissions?
Create an Apache Airflow user on the Viewer role.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint reaches Apache Airflow from any client.
Claude, ChatGPT and Cursor connect over OAuth, no SDK and no shared key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
11 Apache Airflow tools, no custom code.
Read, create, update and delete users and roles across Apache Airflow resources and methods.
- List all Apache Airflow users
- Get single Apache Airflow user by ID
- Create a Apache Airflow user
- Update a Apache Airflow user by ID
ElaichiToolsToolboxes
Every team gets its own Airflow toolbox.
Curate Apache Airflow toolboxes per team, from platform engineering to data operations.
- Platform engineering
- Data engineering
- Analytics
- Security
ElaichiToolboxesShared connections
Teammates use Airflow without seeing a credential.
The connections table shows who connected each Apache Airflow account and its sharing.
- Platform prod
- Data engineering
- Analytics EMEA
- Security review
ElaichiConnectionsAudit log
Every Airflow role change has a name on it.
When, who, what happened, type and resource for each Apache Airflow call.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching 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 audits Airflow roles end to end.
Six steps fetch users and roles, group them, draft a digest, then post back.
Apache Airflow digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch users
Apache Airflow
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
Apache Airflow
Queued
Collections and dashboards
Airflow user and role numbers, computed on schedule.
Four metrics, 14 days of users created and a breakdown by team.
Apache Airflow health
Refreshed 4 minutes ago · every 15 minutes · from the users collection
Users
1,284 ↓ 12%
Roles
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Users created
Last 14 days
By team
Share of activity
Platform prod 34%
Data engineering 27%
Analytics EMEA 21%
Security review 18%
FAQ
Frequently asked questions
How do I connect Apache Airflow to Claude?
Connect Apache Airflow in Elaichi first: paste an Apache Airflow API key when prompted, and the connection is ready. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint.
Does Apache Airflow work with ChatGPT and Cursor as well as Claude?
Yes. Once Apache Airflow 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 Apache Airflow once and every client can use it.
What can an AI agent actually do with my Apache Airflow data?
With this connector an agent can list Apache Airflow users, look up a single user, create new accounts, update them, and remove them. It can do the same for Apache Airflow roles, and it can list the permissions available in your deployment. It does not run or edit pipelines; this connector is about who has access to Apache Airflow and what they are allowed to do.
Does connecting Apache Airflow give the AI every user and role?
The AI only sees what the Apache Airflow API key it runs under is allowed to see, and every action is logged against the person who signed in to Elaichi. Elaichi can narrow that access further, for example to read-only on Apache Airflow users and roles, but it can never grant more than the key itself has.
Can I stop an agent from deleting or changing things in Apache Airflow?
Yes. Restrictions in Elaichi apply per action, so you can allow listing and looking up Apache Airflow users and roles while blocking create, update, and delete. A blocked action is never shown to the AI client at all, so no prompt, however worded, can reach it.
What happens to an Apache Airflow connection when someone leaves?
When you offboard someone in Elaichi, their access to Apache Airflow through Elaichi ends at once, across every client they used. If the connection was shared, it keeps working for everyone else on the team. Disconnecting Apache Airflow once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client in one step.
Put Apache Airflow in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.