Create and deploy Model Context Protocol (MCP) servers by using an OpenAPI file and a set
of supported commands.
About this task
You can use the MCP client tool to streamline the extension of your API Agent's capabilities by
connecting to external services and tools.
By using the MCP tool, you can do the following key actions.
- Dynamically create and deploy MCP servers from OpenAPI 3.0 specifications
- Enable and interact with external or internal MCP servers
- Run operations on any compliant server by using natural language prompts
- Automatically generate tool interfaces and schemas based on server definitions
Procedure
To configure the MCP server, complete the following steps.
- In Visual Studio Code, open API Agent. To know more
information about how to use API Agent in Visual Studio
Code, see Getting started.
- In the Type something field, enter the following prompt.
Create an MCP server from [@insert file here]
API Agent displays
the proposed plan.
- Click Start.
- Download the compressed file and save it in your Visual Studio Code workspace.
Note: Ensure that YAML or compressed files are available in the Visual Studio Code workspace so that
API Agent can access
them.
- To run the server locally, click the Deploy the application code using [zip
file] instruction.
- Delete the brackets, and select the compressed file.
- In the proposed plan, click Start.
- To check the deployment status, enter the following prompt.
Give me the deployment status for the application code file @output.zip
After the successful deployment, API Agent displays a URL
where the MCP server is deployed.
- To configure the external MCP server, enter the following prompt.
Enable the MCP server for github with description 'GitHub integration for
repository management',deployed_url: [Add URL],authentication: [Add token number]
