Introduction
MCP, or Model Context Protocol, is an open standard that gives applications a common way to discover and use tools from other systems. Instead of building a custom integration for every tool or service, MCP gives those systems a shared way to describe what they can do and how to call them.
In FME, MCP works in both directions. FME can act as a client by using the MCPCaller transformer to call tools from external MCP servers. FME Flow can also act as an MCP server by exposing FME workspaces as tools that MCP-compatible clients can discover and run.
That means FME can use tools from the broader MCP ecosystem, and it can also make FME workflows available to AI agents or other MCP clients.
Consuming MCP
The MCPCaller lets an FME workspace call capabilities hosted by external MCP servers. Use MCPCaller when you want a workspace to reach another MCP-enabled system during a translation, send inputs to an external tool, receive the result, and use that result in the rest of the workflow.
Serving MCP
FME Flow can act as an MCP server by exposing FME workspaces as MCP tools. Use FME Flow as an MCP server when you want MCP-compatible clients to discover and run FME workflows through a standard interface.
Terminology
- MCP (Model Context Protocol): An open standard that gives applications a consistent way to connect to external systems, discover what capabilities they expose, and invoke them. Any MCP client can work with any MCP server, regardless of the underlying technology.
- MCP Server: A system that makes its capabilities available through MCP. FME Flow, for example, acts as an MCP server when it exposes workspaces as callable tools.
- MCP Client: An application that connects to an MCP server to discover and use its capabilities. FME acts as an MCP client when the MCPCaller invokes tools from an external server.
- MCP Tool: An operation a client can invoke on an MCP server. Tools accept defined inputs, execute an operation, and return structured results. Operations can include anything from data retrieval and updates to processing, analysis, or complex workflow logic.
- MCP Resource: Data that an MCP server makes available for clients to read, such as files, records, or documents. Unlike tools, resources are not invoked — they are accessed directly.
- MCP Prompt: A reusable template provided by an MCP server, typically used to supply context or instructions to a client.
- MCPCaller: The FME package used to connect a workspace to an external MCP server and call its tools, resources, or prompts from within a workflow.
Articles
Getting Started with the MCPCaller
How to use the MCPCaller Transformer to connect FME workflows to external MCP servers.
Getting Started with FME Flow as an MCP Server
How to expose FME Flow workspaces as MCP tools.
Additional Resources
FME with MCP: The Power of Choice, Expanded: Overview of FME's MCP capabilities, including the MCPCaller Transformer and FME Flow's MCP Server, with use cases and FAQs.
The Model Context Protocol: A Universal Bridge Between Your Data and AI: Conceptual overview of MCP — what it is, how it works, and how FME fits into the ecosystem as both a consumer and provider of MCP capabilities.
MCP and the Power of Choice: Expanding Your AI and System Reach (webinar): Introductory walkthrough of both FME MCP capabilities with live demos — consuming MCP tools with the MCPCaller and creating MCP tools in FME Flow.
From Esri to AI: Create an MCP Server in 7 Minutes with FME (webinar): Live build turning an FME workspace into a functional MCP server, using ArcGIS data as a starting point. Covers the full pattern from workspace to MCP tool.
From Prototype to Production: Building Real-World AI and MCP Workflows (webinar): Intermediate-level session with real municipal use cases, covering generative AI for document extraction, the FME Flow MCP server in practice, and lessons learned from production deployments.