Petstore MCP server
{
"mcpServers": {
"mcp-petstore": {
"type": "http",
"url": "https://petstore.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-petstore": {
"type": "http",
"url": "https://petstore.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-petstore": {
"type": "http",
"url": "https://petstore.run.mcp.com.ai/mcp"
}
}
}{
"servers": {
"mcp-petstore": {
"type": "http",
"url": "https://petstore.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-petstore": {
"type": "http",
"url": "https://petstore.run.mcp.com.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 0.6.0
What it does
HAPI MCP transforms OpenAPI/Swagger specifications into MCP servers automatically, exposing API endpoints as tools for AI agents and LLMs. It is for developers who want to make existing REST APIs available to MCP clients without rewriting business logic.
- Convert a Swagger/OpenAPI spec into MCP tools and use them with ChatGPT, Claude, or other MCP clients.
- Expose an internal REST API as a set of deterministic tools for agentic workflows using OrcA orchestration.
- Test and prototype multi-tool integrations by lifting existing APIs into the MCP ecosystem with a single CLI command.
This entry comes from the registry but points to no public repository, so there is nothing to check: no commit history, no source, no tool list. It is listed for completeness and left out of search engines.
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.