MuleSoft Anypoint MCP server

MuleSoft Anypoint is a unified integration platform for building and managing APIs and integrations. An AI agent with access to Anypoint can design APIs, develop integrations, manage the API lifecycle, deploy applications, and monitor runtime performance without manual Anypoint operations.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin

You'll need:

• Access to AI Gateway with permission to create MCP servers
• API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server

Find the API in the catalog

1. Sign in to AI Gateway and select MCP Servers from the left navigation.
2. Select New MCP Server.
3. Search for the application you want to connect, then select it from the catalog.

Configure the server

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
2. Enter a Description so your team knows what the server is for.
3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
4. Toggle Production mode on if this server will be used in a live workflow.
5. Select Next.

Configure authentication

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security

1. Set any Rate limits appropriate for your use case and the API's own limits.
2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
3. Select Next.

Deploy

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

---

Connect to an AI client

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

Tips

• You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
• If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
• You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication

MuleSoft Anypoint uses OAuth 2.0 Client Credentials flow. Create a Connected App in Access Management > Connected Apps and configure it with Client Credentials grant type. The token endpoint is https://anypoint.mulesoft.com/accounts/oauth2/token. Note your organization ID and environment ID (available in Anypoint Settings). Send your client ID and client secret to the token endpoint to obtain access tokens. The API base URL is https://anypoint.mulesoft.com for the control plane and management operations.

Available tools

This MCP server enables API design, integration development, runtime management, and API lifecycle management across the Anypoint platform.

Tool	Description
Create API specification	Create or update RAML or OpenAPI API definition
Get API specification	Retrieve API design and contract
Publish to Exchange	Publish API or asset to Exchange marketplace
Get Exchange asset	Retrieve asset details from Exchange
Create integration project	Create a new Mule integration project
Deploy application	Deploy Mule application to CloudHub or runtime
Get deployment	Retrieve deployment status and configuration
Update deployment	Modify deployment settings like worker size
Scale application	Change number of workers for an application
Get logs	Retrieve application logs from runtime
Monitor application	Get performance metrics and dashboards
Create API proxy	Create proxy endpoint for existing service
Apply policy	Add security or transformation policy to API
Get SLA tier	Retrieve API client subscription tier
Create client app	Register client application for API access
Generate client credentials	Create API key/secret for client application
Track API usage	Retrieve analytics on API consumption
Get event	Retrieve integration events and transactions
List environments	Retrieve available deployment environments
Create environment	Create new deployment environment
Get environment configuration	Retrieve environment settings

Tips

Publish reusable APIs, integrations, and connectors to Exchange — this enables teams to discover and reuse assets across projects.

Use Dev, Test, and Production environments to separate development from production workloads.

Test integrations in lower environments before deploying to production to catch configuration errors and integration issues.

Apply policies to API proxies to add authentication, rate limiting, transformation, and other capabilities to your APIs.

Order policies carefully as execution order matters — policies are applied in the sequence they're listed.

Adjust worker size and count based on throughput requirements to ensure your applications can handle expected traffic.

Monitor application performance and scale up when approaching capacity limits to prevent dropped requests.

Use DataWeave for complex data transformations between systems — mastering DataWeave syntax enables building sophisticated integration patterns.

---