What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the HAPI MCP Server MCP server?
HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants
How to install HAPI MCP Server
Copy-paste configuration for popular MCP clients.
HAPI_FQDNFully Qualified Domain Name for the HAPI server (used in MCP tool URLs)
HAPI_HOMEDirectory path for HAPI configuration and specs. Should be mounted as a volume in Docker
PROJECT_NAMEThe name of the project/API (alternative to positional argument)
HAPI_OPENAPIOpenAPI spec URL or path (alternative to --openapi flag)
HAPI_URLBackend API base URL (alternative to --url flag)
HAPI_PORTServer port (alternative to --port flag) - this is the internal container port
HAPI_HEADLESSEnable headless mode (alternative to --headless flag)
HAPI_MCPEnable MCP mode (alternative to --mcp flag)
HAPI_DEVEnable development mode (alternative to --dev flag)
HAPI_CORSComma-separated allowed CORS origins (alternative to --cors flag)
HAPI_CONFIG_FILESComma-separated configuration files (alternative to --filename flag)
NODE_ENVNode environment (development, production). 'development' enables verbose logging and debugging features.
{
"mcpServers": {
"hapi-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/hapimcp/hapi-cli:0.6.0",
"-p",
"-v",
"serve",
"petstore",
"--port",
"--headless",
"--mcp",
"--dev",
"--url",
"--openapi",
"--cors",
"--filename",
"--cert",
"--key"
],
"env": {
"HAPI_FQDN": "<YOUR_HAPI_FQDN>",
"HAPI_HOME": "<YOUR_HAPI_HOME>",
"PROJECT_NAME": "<YOUR_PROJECT_NAME>",
"HAPI_OPENAPI": "<YOUR_HAPI_OPENAPI>",
"HAPI_URL": "<YOUR_HAPI_URL>",
"HAPI_PORT": "<YOUR_HAPI_PORT>",
"HAPI_HEADLESS": "<YOUR_HAPI_HEADLESS>",
"HAPI_MCP": "<YOUR_HAPI_MCP>",
"HAPI_DEV": "<YOUR_HAPI_DEV>",
"HAPI_CORS": "<YOUR_HAPI_CORS>",
"HAPI_CONFIG_FILES": "<YOUR_HAPI_CONFIG_FILES>",
"NODE_ENV": "<YOUR_NODE_ENV>"
}
}
}
}Related MCP servers
Transform OpenAPI specs into MCP tools instantly—no rewrites, no parallel codebases.

LinkedIn MCP Server
Turn LinkedIn's API into AI-ready MCP tools—retrieve profiles and publish content instantly.

OpenAI Tools MCP Server
Transform OpenAPI specs into MCP tools instantly—no rewrites, no parallel codebases.

Petstore MCP Server
Transform OpenAPI specs into MCP tools instantly—no rewrites, no sidecar servers.

MCP Registry Server
Official MCP Registry: publish and discover MCP servers like an app store for AI agents.

Search and discover Agent Skills — reusable AI agent capability packages — from the skills.sh registry.