Mule 4 MCP connector
home
Anypoint Connector for MCP (MCP Connector) uses the Model Context Protocol (MCP) to enable AI clients that support MCP to invoke and interact with APIs, connectors, and apps.
Use MCP Connector to connect LLM applications with your APIs. Expose APIs with complex endpoints as simpler, more atomic tools or resources that are better suited for agentic clients. Decide on what is straightforward, repeatable, and optimal for agent actions, and start there.
MCP is an open protocol that enables integration between LLM applications and external data, services, and tools.
The MCP protocol:
- Enhances AI precision by supplying AI with relevant information, leading to more accurate responses.
- Empowers AI to manage intricate tasks that require access to external data or services.
- Promotes interoperability between AI models and external systems, simplifying integration into workflows.
MCP Connector:
- Enables you to expose your Mule apps, connectors, custom APIs using the MCP protocol to further enable agentic experiences from agents in Claude, Cursor, Windsurf, and your own agents.
- Enables you to write Mule apps that can act as both an MCP server and a client. The resulting MCP server or client runs inside of Mule, which means you don’t need to configure your own hosting environment.
- When acting as an MCP server, Mule allows AI clients to use existing API-led investments, legacy systems, and SaaS applications that don’t natively support MCP.
- When acting as an MCP client, Mule helps you create connections and orchestrations where AI Agents are added as just another system in the workflow
- Allows you to incorporate AI agents into your existing Enterprise ecosystem, using Mule as the orchestration layer.
- Supports Streamable HTTP for both server and client (recommended) and SSE (for both server and client) transport methods.
- Supports custom response headers on every exposed endpoint, including `/sse`, `/messages`, and `/mcp`. Use custom response headers for security, operational, integration, and governance benefits.
This makes the capabilities of your Mule APIs and applications available to a growing ecosystem of AI agents.
For information about compatibility and fixed issues, see the MCP Connector Release Notes.
Before You Begin
To use this connector, you must be familiar with:
- Anypoint Connectors
- Mule runtime engine (Mule)
- Elements and global elements in a Mule flow
- How to create a Mule app using Anypoint Code Builder or Anypoint Studio
Before creating an app, you must have:
- Java 17
- Apache Maven
- Anypoint Platform
- Credentials to connect with the target resource
- The latest versions of Anypoint Code Builder or Anypoint Studio
Common Use Cases for the Connector
These are some common use cases for the connector:
- Customer ServiceUse AI agents to help human agents be more efficient by handling time-intensive tasks like reviewing case histories, analyzing reported issues, and retrieving relevant information.
- SalesImprove sales teams' success by accelerating prospect research, generating customized collateral, and preparing contracts.
- MarketingEmpower marketing teams with AI-driven support for drafting social media content, conducting market research, and analyzing campaign performance.
Connection Types
- Streamable HTTPAllows you to deploy multiple instances of your MCP server to run behind a load balancer without clients knowing about the individual server URLs. Clients connect to a single endpoint (like `/mcp`) and the load balancer distributes requests across all your MCP server instances. This is particularly useful for scalability in cloud environments, where you might have multiple replicas of your Mule app running.When acting as an MCP client, Streamable HTTP enables your Mule application to connect to remote MCP servers using the same scalable, load-balanced approach.
- SSE ClientEnables MCP Connector to establish a persistent, one-way (server-sent) connection to an MCP server using the Server-Sent Events (SSE) standard. This type of connection allows the MCP server to push real-time updates and messages to the client without the need for the client to constantly poll for new information.
- SSE ServerExposes the MCP server using the Server-Sent Events (SSE) transport. This allows MCP clients to establish persistent, one-way connections to this server to receive real-time updates and messages.
Next Step
After you complete the prerequisites, you are ready to create an app and configure the connector using Anypoint Studio or Anypoint Code Builder.