HAPI MCP transforms existing OpenAPI specifications into Model Context Protocol (MCP) servers, allowing APIs to be used as AI-ready tools without rewriting business logic.
From the registry: Swagger Petstore API (v1.0.27) as MCP for testing and prototyping powered by the HAPI MCP server
Please install the `petstore` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **HAPI CLI** — Install HAPI CLI from GitHub releases (https://github.com/la-rebelion/hapimcp/releases)
Canonical MCP server config (stdio transport):
- command: `hapi`
- args: ["serve","path/to/your/swagger.json","--headless"]
Note: HAPI MCP converts OpenAPI/Swagger specs into MCP servers. The 'petstore' slug appears to be an example/demo. Replace swagger.json path with your own OpenAPI spec. Hosted HAPI server at hapi.mcp.com.ai.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.