mcpField
O
Openapi Inspector

Openapi Inspector

Local
github.com/NonetssDeveloper Tools0Updated 39w ago

About Openapi Inspector

Openapi Inspector is an OpenAPI MCP server for frontend development and backend contract verification. It lets LLMs explore API specifications on demand, generate types and code snippets, and check response data against the contract.

Key features

  1. 01Browse and search categorized endpoints
  2. 02Retrieve request and response JSON schemas
  3. 03Generate TypeScript types and Zod schemas
  4. 04Generate data-fetching code and mock data
  5. 05Validate responses and map dependencies
  6. 06Inspect security requirements and call endpoints

Use cases

  1. 01Generate frontend types and validation schemas from an API spec
  2. 02Create mock data for UI prototypes
  3. 03Check backend responses against an API contract
  4. 04Explore endpoints and their data dependencies

MCP support

It exposes OpenAPI endpoint exploration, schema retrieval, code generation, and response validation tools to MCP clients; it can also configure authentication and call APIs.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"none.api": {
"command": "npx",
"args": [
"-y",
"@nonetss/none.api"
],
"env": {
"OPENAPI_URL": "<OPENAPI_URL>"
}
}
}
}
Run commandnpx -y @nonetss/none.api
Environment variables to set
OPENAPI_URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@nonetss/none.api

Tools

17

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
limitnumberNoLimit the number of results (default: 50).
offsetnumberNoStarting index for pagination (default: 0).

Details

From the project README

none.api - OpenAPI Explorer MCP Server

Professional OpenAPI explorer for the Model Context Protocol (MCP), optimized for Frontend Development and Backend Contract Verification.

What is this?

This MCP server allows Large Language Models (LLMs) like Claude or Cursor to dynamically explore, understand, and interact with any API that has an OpenAPI/Swagger specification.

It is specifically designed to:

  1. Accelerate Frontend Development: Generate types, Zod schemas, mock data, and data-fetching hooks (Axios/TanStack Query) directly from the API definition.
  2. Verify Backend Implementation: Validate backend response objects against the OpenAPI contract to ensure the implementation matches the specification.
Installation
Using npx (Recommended)

You can run the server directly without installation:

npx @nonetss/none.api
Global Installation
npm install -g @nonetss/none.api
Key Features
  • Smart Exploration: Categorized endpoint listing and keyword-based search (with multilingual synonym support).
  • Frontend Factory:
    • Generate TypeScript Interfaces for requests and responses.
    • Generate Zod Schemas for form validation.
    • Generate React/Axios/TanStack Query snippets.
    • Generate Mock Data for UI prototyping.
  • Backend Guard:
    • Response Validation: Compare JSON data against OpenAPI schemas using AJV.
    • Dependency Mapping: Understand relationships between resources (e.g., which endpoint provides the ID needed for another).
  • Security: Automatic authentication support (Bearer/API Key) and secure environment-locked configuration.
Tools Overview
ToolFocusDescription
list_endpointsExplorationLists all endpoints grouped by functional categories.
list_tagsExplorationLists all tags (functional categories) in the API.
search_by_tagExplorationLists all endpoints associated with a specific tag.
find_endpointExplorationIntelligent search by intent or keyword (e.g., "delete user").
get_endpoint_infoAnalysisDetailed documentation, parameters, and response codes.
get_request_schemaAnalysisReturns the JSON schema for an endpoint's request body.
get_response_schemaAnalysisReturns the JSON schema for a specific response status code.
get_typescript_typesFrontendGenerates ready-to-use TypeScript interfaces.
get_zod_schemaFrontendGenerates Zod validation schemas.
get_framework_snippetFrontendGenerates Axios or TanStack Query code.
get_fetch_snippetFrontendGenerates a native fetch snippet for quick integration.
get_mock_dataPrototypingGenerates high-fidelity mock data based on schemas.
map_dependenciesArchitectureAnalyzes data flow and ID relationships between routes.
get_security_infoSecurityShows security requirements for the API or specific routes.
set_security_contextSecuritySets authentication headers for subsequent requests.
call_endpointDebugExecutes real HTTP calls to the configured API.
validate_responseBackendValidates a JSON object against the API contract.
Configuration

Add this to your claude_desktop_config.json or Cursor MCP settings:

{
  "mcpServers": {
    "none.api": {
      "command": "npx",
      "args": ["-y", "@nonetss/none.api"],
      "env": {
        "OPENAPI_URL": "http://localhost:3000/doc",
        "AUTH_EMAIL": "[email protected]",
        "AUTH_PASSWORD": "your-password",
        "AUTH_PATH": "/api/auth/login"
      }
    }
  }
}
Development Workflow
  1. Build: npm run build (uses tsc + tsc-alias for path resolution).
  2. Formatting: Prettier is included.
  3. Git Hooks: Automated formatting on commit via husky and lint-staged.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.