Swagger/OpenAPI MCP Server
Allows LLMs to explore and interact with Swagger/OpenAPI specifications, providing tools for loading API specifications, browsing endpoints, and getting detailed information about API operations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Swagger/OpenAPI MCP Server load the Petstore API from https://petstore.swagger.io/v2/swagger.json"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Swagger/OpenAPI MCP Server
A Model Context Protocol (MCP) server that allows LLMs to explore and interact with Swagger/OpenAPI specifications. This server provides tools and resources for loading API specifications, browsing endpoints, and getting detailed information about API operations.
Installation
Clone or create the project directory
Install dependencies:
npm installBuild the TypeScript code:
npm run buildRelated MCP server: OpenAPI MCP Server
Usage
Available Tools
load_api
Load an OpenAPI/Swagger specification into the server.
Parameters:
apiId(string): Unique identifier for this APIsource(string): URL or file path to the OpenAPI/Swagger specification
Example:
{
"name": "load_api",
"arguments": {
"apiId": "petstore",
"source": "https://petstore.swagger.io/v2/swagger.json"
}
}get_endpoint_details
Get detailed information about a specific API endpoint.
Parameters:
apiId(string): ID of the loaded APImethod(string): HTTP method (GET, POST, etc.)path(string): API endpoint pathnatural(boolean, optional): If true, returns a human-readable summary
Example:
{
"name": "get_endpoint_details",
"arguments": {
"apiId": "petstore",
"method": "GET",
"path": "/pet/{petId}",
"natural": true
}
}list_apis
List all currently loaded API specifications.
Parameters: None
search_endpoints
Search for endpoints matching a specific pattern.
Parameters:
apiId(string): ID of the loaded APIpattern(string): Search pattern for endpoint paths or descriptions
Example:
{
"name": "search_endpoints",
"arguments": {
"apiId": "petstore",
"pattern": "pet"
}
}Available Resources
swagger://{apiId}/load
Get overview information about a loaded API specification.
swagger://{apiId}/endpoints
Get a list of all available endpoints for an API.
swagger://{apiId}/endpoint/{method}/{path}
Get detailed information about a specific endpoint.
Configuration with Claude Desktop
To use this server with Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"swagger-explorer": {
"command": "node",
"args": ["/path/to/your/swagger-mcp-server/build/index.js"]
}
}
}Replace /path/to/your/swagger-mcp-server with the actual path to your project directory.
License
MIT License
Available Tools
4 toolsget_endpoint_detailsD
Inputs: apiId (required), method (required), path (required), natural.
list_apisD
Inputs: no named parameters.
load_apiD
Inputs: apiId (required), source (required).
search_endpointsD
Inputs: apiId (required), pattern (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: get_endpoint_details retrieves specific endpoint information, list_apis enumerates available APIs, load_api loads an API specification, and search_endpoints searches across endpoints. There is no overlap or ambiguity in their functions.
All tool names follow a consistent verb_noun pattern (get_endpoint_details, list_apis, load_api, search_endpoints). The naming is uniform and predictable, using snake_case throughout with clear action-object pairs.
With only 4 tools, the set feels thin for a Swagger/OpenAPI server, which typically involves operations like validating, updating, or testing APIs. While the core functions are covered, the scope could benefit from additional tools for a more comprehensive API management surface.
The tools cover basic operations (list, load, get, search), but there are notable gaps for a full API lifecycle, such as creating, updating, or deleting APIs/endpoints, and validating specifications. Agents can perform read and search tasks but may hit dead ends for modification workflows.
Related MCP Connectors
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA server that enables Large Language Models to discover and interact with REST APIs defined by OpenAPI specifications through the Model Context Protocol.12,706 npm302MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol Server that enables LLMs to interact with and execute REST API calls through natural language prompts, supporting GET/PUT/POST/PATCH operations on configured APIs.6Apache 2.0
- AlicenseBqualityDmaintenanceA Model Context Protocol server that loads multiple OpenAPI specifications and exposes them to LLM-powered IDE integrations, enabling AI to understand and work with your APIs directly in development tools like Cursor.790MIT

MockLoop MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceA Model Context Protocol server that generates and runs mock API servers from API documentation like OpenAPI/Swagger specs, enabling developers and AI assistants to quickly spin up mock backends for development and testing.18MIT