Application Development
RabbitMQ MCP connector
Connect RabbitMQ to Elaichi and Claude, ChatGPT, Cursor or any MCP client can check cluster health, list nodes, connections and channels, and export or import definitions, with every call logged against the person who asked.
-
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 RabbitMQ to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect RabbitMQ once
-
Open Connections, choose Add connection, and pick RabbitMQ.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a RabbitMQ API key. One person generates a token in RabbitMQ 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 RabbitMQ 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 RabbitMQ 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 RabbitMQ 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 RabbitMQ 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 RabbitMQ through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
On-call
Check whether the cluster is healthy
Run an aliveness test and read the cluster overview during an incident, then ask which nodes are up and how many connections and channels are open right now, all from the chat window you are already in.
-
Platform engineering
Find the node that is running out of memory
List every node in the RabbitMQ cluster and pull its memory breakdown, so you can see which one is under pressure before it starts refusing publishers.
-
Backend
See which service is holding all the connections
List connections by username or by virtual host, then drill into the channels on a single connection to find the consumer that never closed what it opened.
-
Site reliability
Close a runaway connection without a console
When one client is flooding the broker, look up its connection by ID or username and close it, with the action recorded against your name in the audit log.
-
DevOps
Back up and restore virtual host definitions
Export the exchanges, queues, bindings and policies for a virtual host as a definitions file, then import them into a new cluster or a staging environment.
-
Architecture
Prepare a cluster for its next upgrade
List enabled feature flags and any deprecated features still in use, so the upgrade plan is based on what the cluster actually runs rather than what the wiki says.
Try asking
- “Which RabbitMQ nodes are using the most memory now?”
- “Show vhosts missing from last night's RabbitMQ definitions export.”
- “Which deprecated RabbitMQ features are still in use?”
AI tools
RabbitMQ tools for your AI agents
131 tools are ready to call through Elaichi's MCP endpoint the moment you connect RabbitMQ, 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 RabbitMQ gets you
6 screens from the product, each doing one job for your RabbitMQ account.
The agent
Ask about RabbitMQ nodes, get real answers.
Plain language questions answered from live RabbitMQ nodes, queues and definitions.
- nodes
- definitions
- vhosts
- feature flags
Ask Elaichi to work across your apps.
Which RabbitMQ nodes are using the most memory now?
Show vhosts missing from last night's RabbitMQ definitions export.
Which deprecated RabbitMQ features are still in use?
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach RabbitMQ here.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
131 RabbitMQ tools are ready to call.
Nodes, definitions, vhosts and feature flags are covered without custom code.
- List all RabbitMQ aliveness tests
- List all RabbitMQ overviews
- List all RabbitMQ cluster names
- RabbitMQ cluster names bulk update
Toolboxes
Every team gets its own RabbitMQ toolbox.
Platform, SRE and app teams each see the RabbitMQ tools they need.
- Platform
- SRE
- Application Development
- Release Engineering
Shared connections
Teammates use RabbitMQ without seeing credentials.
Each RabbitMQ connection shows who connected it and which teams share it.
- Production cluster
- Staging cluster
- Payments
- Platform EMEA
Audit log
Every RabbitMQ call is recorded permanently.
When, who, what happened, type and resource for each RabbitMQ action.
- 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 turns RabbitMQ records into action.
Six steps fetch nodes, group them, draft a digest, await approval, post back.
RabbitMQ digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch nodes
RabbitMQ
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
RabbitMQ
Queued
Collections and dashboards
RabbitMQ health arrives before anyone asks.
Four metrics, 14 days of records created and a team breakdown, refreshed hourly.
RabbitMQ health
Refreshed 4 minutes ago · every 15 minutes · from the nodes collection
Nodes
1,284 ↓ 12%
Definitions
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Nodes created
Last 14 days
By team
Share of activity
Production cluster 34%
Staging cluster 27%
Payments 21%
Platform EMEA 18%
FAQ
Frequently asked questions
How do I connect RabbitMQ to Claude?
Two steps. First connect RabbitMQ in Elaichi by pasting the API key from your RabbitMQ management interface, there is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi and RabbitMQ is then available in the conversation.
Does RabbitMQ work with ChatGPT and Cursor as well as Claude?
Yes. Once RabbitMQ 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 RabbitMQ once and every client you use picks it up.
What can an AI agent actually do with my RabbitMQ data?
With RabbitMQ connected, an agent can run an aliveness test, read the cluster overview, list nodes and their memory use, list open connections and channels by virtual host, username or connection, close a specific connection, export or import definitions for a virtual host, and report which feature flags and deprecated features are in use. Because RabbitMQ has a large catalog of actions, the agent searches for the right one as you ask, so short concrete requests like "list connections for the orders vhost" work better than long paragraphs.
Does connecting RabbitMQ give the AI access to every virtual host?
No. Access follows the RabbitMQ API key you connected with, so the agent can only see the virtual hosts, nodes and connections that key is allowed to see in RabbitMQ itself. Elaichi can narrow that further by restricting individual actions or hiding parts of the catalog, but it can never grant more than RabbitMQ already permits.
Can I stop an agent from closing connections or importing definitions in RabbitMQ?
Yes. Restrictions in Elaichi work per action, so you can allow reading nodes, connections and channels while blocking closing connections, importing definitions or updating cluster names. A blocked action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however worded, can reach it.
What happens to a RabbitMQ connection when someone leaves?
Offboarding the person in Elaichi ends their access to RabbitMQ at once across every client they used. If they had shared a RabbitMQ connection with a team, it keeps working for everyone else on that team. When you do want to remove RabbitMQ entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Put RabbitMQ in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.