IBM MQ
Connect AI agents and workflows to IBM MQ: put, get and browse messages, publish to topics, run request and reply, and start work as messages arrive.
Book a demoIBM MQ for AI agents and workflows.
engini lets your AI agents and workflows work with IBM MQ, the messaging that carries payments, orders and core-system events in banks and large enterprises: put messages on queues, get or browse them, publish to topics, send a request and wait for the reply, check queue depth, and start a workflow the moment a message arrives. Your queue managers stay where they are, and the On-Prem Agent connects out to engini with no inbound ports. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.
Cursor, your code
audit log
in engini
What your agent can do in IBM MQ. Every tool is one you allow or leave out.
The IBM MQ tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.
Read
Read messages without taking them off the queue.
See what is waiting, and where.
Write
Put a message on a queue, with its headers and properties.
Take a message off a queue, under a transaction.
Put a request and wait for the reply on a reply queue.
Publish a message to every subscriber of a topic.
Triggers
A message arrived on a queue engini watches.
A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.
Connect your AI agent to IBM MQ. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your IBM MQ connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.
MCP client setup →Python and TypeScript
Hand your agent a toolset of IBM MQ tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.
SDK guide →For coding agents
The engini CLI connects IBM MQ and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.
CLI guide →Any language
Every IBM MQ tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.
API reference →.cursor/mcp.json. Claude Code: claude mcp add.// .cursor/mcp.json: Cursor, connected to IBM MQ through engini
{
"mcpServers": {
"engini-ibm-mq": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your IBM MQ connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.
Each request runs through the IBM MQ tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on IBM MQ. Agents and workflows, across systems.
Payments and core events into workflows
A payment or account event on an MQ queue starts a workflow that updates Salesforce, notifies the team and records it in the data warehouse.
Queues that do not back up quietly
When a queue passes its threshold or the error queue fills, the on-call team hears in Slack and a ServiceNow incident opens.
Cloud apps that speak to the core
An order from Shopify or a CRM becomes a message the mainframe or ERP already knows how to process, and the reply comes back.
Answers from the core in real time
An agent sends a request over MQ and answers a customer with the reply. Its toolset holds Request and Reply only.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between IBM MQ and another system engini connects is available.
You decide what each agent may do in IBM MQ. engini enforces it on every call.
Only the tools you allow
A toolset lists the IBM MQ tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.
Scoped when you set them up
An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.
Whose permissions apply
Connect a person's own IBM MQ account and engini acts as that person, with their IBM MQ permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.
Kept out of prompts
Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.
Every call on record
Every call lands in History and the audit log, which you can export or stream to your SIEM.
Test before production
Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.
IBM MQ behind your firewall.
If IBM MQ runs in your own data center, install the engini On-Prem Agent on a server inside your network. It opens every connection itself: out to engini over HTTPS on port 443, and to IBM MQ while it runs a task. You open no inbound ports or firewall rules. Calls through it run on the same engine as MCP, the API and workflows, and each one is recorded in History.
On-Prem Agent guide →Connect IBM MQ in three steps. Then decide what each agent may do.
Sign in to IBM MQ
Install the engini On-Prem Agent on a server that can reach the queue manager, create a channel and user with access only to the queues and topics the workflows need, then add an IBM MQ connection with the host, port, queue manager, channel, user and TLS settings.
Choose the tools
Add the connection to an MCP server or a toolset with only the tools each agent needs.
Build or ask
Use the connection as a step in a workflow, or ask your agent to work in IBM MQ from Claude, ChatGPT, Cursor or your own code.
IBM MQ and engini. Straight answers.
Can an AI agent write to IBM MQ, or only read?
Both. engini has tools to put, get and publish messages and to send requests and wait for replies. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.
Does Get Message remove the message?
Yes, under a transaction, so a failed workflow puts it back. Browse Messages reads without removing anything.
Does it work with IBM MQ on Cloud and in containers?
Yes. Any queue manager the On-Prem Agent, or engini directly, can reach over a client channel.
Does the agent act as me in IBM MQ?
It acts as the MQ user behind the connection, with the queue and topic authority that user has. Every run is recorded under the person who started it.
Can a change in IBM MQ start work?
Yes. A message arriving on a queue engini watches starts a workflow as it arrives. A workflow can include an AI agent step.