Azure Logic Apps Standard Enters MCP Public Preview — Expose Connectors as Agent Tools

What this preview does

Microsoft now allows Azure Logic Apps (Standard) to operate as Model Context Protocol (MCP) servers in public preview. That lets you surface HTTP Request/Response workflows as discoverable, callable agent tools for MCP-capable clients (for example VS Code + Copilot).

What’s included

Reference: https://learn.microsoft.com/en-us/azure/logic-apps/set-up-model-context-protocol-server-standard

Key requirements and transport details

API Center path: preview limits to note

When creating MCP servers via API Center backed by Logic Apps, the preview imposes these constraints:

Why target Standard runtime?

Logic Apps (Standard) runs on the single-tenant runtime (on Azure Functions), supports multiple workflows per app, and integrates with virtual networks and private endpoints. These characteristics make it better suited for exposing private systems safely to agents and for predictable throughput/latency. By contrast, Consumption is multitenant, single-workflow per app, and pay-per-execution.

Tooling semantics and discoverability

Microsoft recommends adding trigger descriptions, parameter schemas/descriptions, and required markers so MCP clients can more reliably select and call tools. These annotations are read by MCP clients and influence invocation behavior.

Connectors and enterprise reach

Organizations can expose existing workflows and many Logic Apps connectors (cloud and on-prem) through MCP — Microsoft cites more than 1,400 connectors — turning them into callable agent tools.

Operations, governance, and testing

Run history plus Application Insights and Log Analytics remain available for diagnostics and audits. VS Code supports quick client validation via MCP: adding a server includes OAuth sign-in and tool enumeration. Registering MCP servers in API Center adds discovery and governance across teams.

Production notes from the preview

Teams already using Logic Apps can adopt this preview as a relatively low-friction, standards-aligned way to operationalize agent tooling for enterprise systems, while watching for API Center limits, SSE prerequisites, and Easy Auth nuances.