iQBus ships with a built-in MCP Server. Connect the AI assistant your team already uses and it can design, build and monitor integrations on iQBus, under access levels you set, in your own Azure tenant.

Describe the integration to your agent. Through the MCP Server it creates the ports, pipelines, pipeline components, maps and promoted properties on iQBus, end to end. Your team adds the credentials and reviews the result before it is used.
Tell your agent, in plain language, what should come in, how it should change and where it should go.
Ports, pipelines, components, maps, promoted properties and subscriptions, created through the MCP Server as real iQBus configuration.
People add the credentials, check the result in iQBus and put it to work. No build, no release window, no restart.
Three access levels, switched per environment. Choose one to see what an agent can and cannot do.
Every action an agent takes is authenticated through Microsoft Entra ID and recorded in iQBus Auditing, like any change made by a person.
MCP is the protocol AI assistants use to work with the tools around them. iQBus speaks it natively, so you are not tied to one AI vendor, and nothing leaves your Azure tenant.
Any MCP client can connect. Use the assistant your team already pays for, or build your own.
Agents sign in through Microsoft Entra ID with OAuth 2.1 and act within the permissions you grant. The access level is set per environment, so an agent can have Full access in test and Structure in production.
What an agent creates or changes is recorded in iQBus Auditing, the same way as a change made by a person. iQBus supports SOC 2 and HIPAA, and runs inside your own Azure tenant.
Security and complianceAn assistant that answers questions is useful. An agent that builds the whole integration end to end, ports, pipelines, components, maps, promoted properties and routing, inside a governed enterprise service bus, changes how fast a new interface gets done, and who can ask for one.
Every plan has AI inside iQBus. Grow and Enterprise open iQBus to the agents outside it.
Starter
AI Accelerator
Grow
AI Accelerator + MCP Server
Enterprise
AI Accelerator + MCP Server
Describe one interface your team has been waiting on. An integration architect will walk through how an agent would build it on iQBus, what it would need from you, and which access level fits your environment.
You'll speak with a senior integration architect, not an SDR.
MCP (Model Context Protocol) is the open standard AI assistants use to work with external tools. iQBus includes an MCP Server, so an AI agent your team already uses — Claude, Microsoft Copilot, an agent in VS Code, or one you build yourself — can connect to iQBus and design, build and monitor integrations through it.
A complete integration: receive and send ports, pipelines and pipeline components, maps, promoted properties and the subscriptions that route messages. A person still adds credentials and secrets and reviews the result before it is used.
Only if you let it. The MCP Server has three access levels, set per environment. Off allows no outside agents at all. Structure lets an agent build the architecture of an integration and see global monitoring, but never any message content. Full access lets the agent do everything iQBus does, within the permissions you grant.
Any client that speaks MCP. That includes Claude, Microsoft Copilot and Copilot Studio, GitHub Copilot in VS Code, and custom agents built on the major agent frameworks. You are not tied to one AI vendor.
The MCP Server runs inside your own Azure tenant as part of iQBus. Agents authenticate through Microsoft Entra ID with OAuth 2.1, and every action is recorded in iQBus Auditing, like any other change. iQBus supports SOC 2 and HIPAA.
The MCP Server is included in the Grow and Enterprise plans. The Starter plan keeps the built-in iQBus AI Accelerator, which drafts pipeline components, custom functions and maps inside iQBus.