Skip to main content
Glama
deenesjakoruzh
Vizioz

Swagger MCP

by Vizioz
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Swagger MCP

An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.

Features

  • Downloads a Swagger specification and stores it locally for faster reference.

  • Returns a list of all the endpoints and their HTTP Methods and descriptions

  • Returns a list of all the models

  • Returns a model

  • Returns service to connect to the end point

  • Returns MCP function definitions

  • Generates complete MCP tool definitions with full schema information

  • Includes AI-specific instructions in tool descriptions

Related MCP server: Mcp-Swagger-Server

Prerequisites

  • Node.js (v14 or higher)

  • npm or yarn

Installation

  1. Clone the repository:

git clone https://github.com/readingdancer/swagger-mcp.git
cd swagger-mcp

  1. Install dependencies:

npm install

  1. Create a .env file based on the .env.example file:

cp .env.example .env

  1. Update the .env file.

Configuration

Edit the .env file to configure the application:

  • PORT: The port on which the server will run (default: 3000)

  • NODE_ENV: The environment (development, production, test)

  • LOG_LEVEL: Logging level (info, error, debug)

Usage

Building the application

Build the application:

npm run build

This will compile the TypeScript code ready to be used as an MCP Server

Running as an MCP Server

To run as an MCP server for integration with Cursor and other applications:

node build/index.js

You can also provide a Swagger URL via CLI argument:

node build/index.js --swagger-url="https://petstore.swagger.io/v2/swagger.json"

Or using the alternative format:

node build/index.js --swaggerUrl="https://petstore.swagger.io/v2/swagger.json"

Note: The CLI --swagger-url argument takes priority over the swaggerFilePath parameter in tool calls. If both are provided, the CLI argument will be used.

Using the MCP Inspector

To run the MCP inspector for debugging:

npm run inspector

Adding to Cursor

To add this MCP server to Cursor:

  1. Open Cursor Settings > Features > MCP

  2. Click "+ Add New MCP Server"

  3. Enter a name for the server (e.g., "Swagger MCP")

  4. Select "stdio" as the transport type

  5. Enter the command to run the server:

    • Basic: node path/to/swagger-mcp/build/index.js

    • With Swagger URL: node path/to/swagger-mcp/build/index.js --swagger-url="https://your-api-url/swagger.json"

  6. Click "Add"

The Swagger MCP tools will now be available to the Cursor Agent in Composer.

Tip: If you provide the --swagger-url CLI argument when configuring the server, you won't need to provide swaggerFilePath in tool calls, making the tools easier to use.

Available Swagger MCP Tools

The following tools are available through the MCP server:

  • getSwaggerDefinition: Downloads a Swagger definition from a URL

  • listEndpoints: Lists all endpoints from the Swagger definition (optional swaggerFilePath)

  • listEndpointModels: Lists all models used by a specific endpoint (optional swaggerFilePath)

  • generateModelCode: Generates TypeScript code for a model (optional swaggerFilePath)

  • generateEndpointToolCode: Generates TypeScript code for an MCP tool definition (optional swaggerFilePath)

Swagger Definition Priority: The tools determine which Swagger definition to use based on this priority:

  1. CLI --swagger-url argument (if provided when starting the server)

  2. swaggerFilePath parameter (if provided in the tool call)

  3. Error if neither is available

If you start the server with --swagger-url, you can omit the swaggerFilePath parameter in tool calls for convenience.

Available Swagger MCP Prompts

The server also provides MCP prompts that guide AI assistants through common workflows:

  • add-endpoint: A step-by-step guide for adding a new endpoint using the Swagger MCP tools

To use a prompt, clients can make a prompts/get request with the prompt name and optional arguments:

{
  "method": "prompts/get",
  "params": {
    "name": "add-endpoint",
    "arguments": {
      "swaggerUrl": "https://petstore.swagger.io/v2/swagger.json",
      "endpointPath": "/pets/{id}",
      "httpMethod": "GET"
    }
  }
}

The prompt will return a series of messages that guide the AI assistant through the exact process required to add a new endpoint.

Setting Up Your New Project

There are two ways to set up the Swagger definition for your project:

Method 1: Using CLI Argument (Recommended)

Start the MCP server with the --swagger-url argument:

node build/index.js --swagger-url="https://your-api-url/swagger.json"

This automatically downloads and caches the Swagger definition. All tools will use this definition, and you won't need to provide swaggerFilePath in tool calls.

Method 2: Using getSwaggerDefinition Tool

Alternatively, you can ask the agent to get the Swagger file using the getSwaggerDefinition tool. Make sure you provide the URL for the swagger file, or at least a way to find it. This will download the file and save it locally with a hashed filename. The filename will automatically be added to a .swagger-mcp settings file in the root of your current solution.

Auto generated .swagger-mcp config file

When using the getSwaggerDefinition tool (Method 2 above), a .swagger-mcp file is automatically created:

SWAGGER_FILEPATH = TheFullPathToTheLocallyStoredSwaggerFile

This configuration file associates your current project with a specific Swagger API. We may use it to store more details in the future.

Once configured, you can reference the Swagger file path from this config file when calling tools. However, if you use the CLI --swagger-url argument (Method 1), this config file is optional as the Swagger definition is automatically loaded.

Improved MCP Tool Code Generator

The MCP tool code generator has been enhanced to provide more complete and usable tool definitions:

Key Improvements

  1. Complete Schema Information: The generator now includes full schema information for all models, including nested objects, directly in the inputSchema.

  2. Better Parameter Naming: Parameter names are now more semantic and avoid problematic characters like dots (e.g., taskRequest instead of task.Request).

  3. Semantic Tool Names: Tool names are now more descriptive and follow consistent naming conventions based on the HTTP method and resource path.

  4. Support for YAML Swagger Files: The generator now supports both JSON and YAML Swagger definition files.

  5. Improved Documentation: Generated tool definitions include comprehensive descriptions for all parameters and properties.

  6. No External Dependencies: The generated code doesn't require importing external model files, making it more self-contained and easier to use.

  7. AI-Specific Instructions: Tool descriptions now include special instructions for AI agents, helping them understand how to use the tools effectively.

Example Usage

To generate an MCP tool definition for an endpoint:

import generateEndpointToolCode from './services/generateEndpointToolCode.js';

// If server was started with --swagger-url, swaggerFilePath is optional
const toolCode = await generateEndpointToolCode({
  path: '/pets',
  method: 'POST',
  swaggerFilePath: './petstore.json', // Optional if --swagger-url was provided
  singularizeResourceNames: true
});

console.log(toolCode);

This will generate a complete MCP tool definition with full schema information for the POST /pets endpoint.

Note: If you started the server with --swagger-url, you can omit the swaggerFilePath parameter:

const toolCode = await generateEndpointToolCode({
  path: '/pets',
  method: 'POST',
  singularizeResourceNames: true
});

License

This project is licensed under the MIT License - see the LICENSE file for details.

MCP Prompts for AI Assistants

To help AI assistants use the Swagger MCP tools effectively, we've created a collection of prompts that guide them through common tasks. These prompts provide step-by-step instructions for processes like adding new endpoints, using generated models, and more.

Check out the PROMPTS.md file for the full collection of prompts.

Example use case: When asking an AI assistant to add a new endpoint to your project, you can reference the "Adding a New Endpoint" prompt to ensure the assistant follows the correct process in the right order.

Available Tools

5 tools
execute_api_requestC

Execute an API request to a specific endpoint

ParametersJSON Schema
NameRequiredDescriptionDefault
methodYesHTTP method (GET, POST, PUT, DELETE, etc.)
pathYesThe endpoint path (e.g., '/users/123')
paramsNoQuery parameters as key-value pairs
bodyNoRequest body as a JSON object (for POST/PUT/PATCH)
headersNoCustom headers as key-value pairs

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool executes an API request but fails to describe critical traits such as authentication requirements, error handling, rate limits, side effects (e.g., whether it modifies data), or response format. This leaves significant gaps for a tool that could perform destructive operations like DELETE.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a general-purpose tool, though it could be more front-loaded with key details if it were more comprehensive.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of executing arbitrary API requests (with potential for mutations, auth needs, etc.), no annotations, and no output schema, the description is incomplete. It doesn't address behavioral aspects, return values, or usage context, making it inadequate for safe and effective tool selection by an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all 5 parameters thoroughly. The description adds no additional meaning beyond what's in the schema (e.g., it doesn't clarify parameter interactions or provide examples), resulting in a baseline score of 3 where the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the action ('execute') and resource ('API request to a specific endpoint'), which provides a basic purpose. However, it lacks specificity about what kind of API or system this targets, and it doesn't clearly differentiate from sibling tools like 'fetch_swagger_info' or 'validate_api_response', which might involve similar API interactions but for different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context (e.g., for testing or production calls), or exclusions, leaving the agent to infer usage based on the generic name and parameters alone, which is insufficient given the presence of sibling tools like 'get_endpoint_details' or 'list_endpoints'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fetch_swagger_infoC

Fetch Swagger/OpenAPI documentation to discover available API endpoints

ParametersJSON Schema
NameRequiredDescriptionDefault
urlNoURL to the swagger.json or swagger.yaml file. If not provided, will try to use the base URL with common Swagger paths.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it behaves—such as whether it makes network requests, handles errors, returns structured data, or has any side effects. This leaves significant gaps for an agent to understand the tool's operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that efficiently conveys the tool's purpose without any wasted words. It's appropriately sized and front-loaded, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete for a tool that likely returns complex API documentation. It doesn't explain what the output looks like (e.g., JSON/YAML structure), potential errors, or how it interacts with sibling tools, leaving the agent with insufficient context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the schema already documents the single parameter ('url') adequately. The description adds no additional meaning or context about the parameter beyond what's in the schema, such as examples or constraints, but this is acceptable given the high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('fetch') and resource ('Swagger/OpenAPI documentation'), and indicates what it's used for ('to discover available API endpoints'). However, it doesn't explicitly differentiate this from sibling tools like 'list_endpoints' or 'get_endpoint_details', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'list_endpoints' or 'get_endpoint_details'. It mentions the purpose but doesn't specify scenarios, prerequisites, or exclusions that would help an agent choose between these related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_endpoint_detailsB

Get detailed information about a specific API endpoint

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesThe endpoint path to get details for (e.g., '/users/{id}')
methodYesThe HTTP method (GET, POST, PUT, DELETE, etc.)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves information, implying a read-only operation, but doesn't specify aspects like authentication requirements, rate limits, error handling, or the format of the returned details. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every part earns its place by directly stating the tool's function, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It clarifies the purpose but lacks behavioral details and usage guidelines. Without an output schema, it doesn't explain return values, which could be a gap, but the description focuses on the input aspect, making it borderline complete for a basic read operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with clear descriptions for both parameters ('path' and 'method'), so the schema does the heavy lifting. The description adds no additional parameter semantics beyond implying that these inputs identify a 'specific API endpoint', which is already inferred from the schema. Baseline 3 is appropriate as the schema provides adequate documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('detailed information about a specific API endpoint'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'fetch_swagger_info' or 'list_endpoints', which likely provide similar API information but with different scopes or formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. With siblings like 'fetch_swagger_info' (which might retrieve broader API documentation) and 'list_endpoints' (which might list endpoints without details), the description lacks context for selection, leaving the agent to infer usage based on tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_endpointsB

List all available API endpoints after fetching Swagger documentation

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that endpoints are listed 'after fetching Swagger documentation', hinting at a dependency or sequence, but it doesn't describe what 'list' entails (e.g., format, pagination, or if it's a read-only operation). For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core action ('List all available API endpoints') and adds necessary context ('after fetching Swagger documentation'). There is no wasted verbiage, and every part of the sentence contributes to understanding the tool's purpose and sequence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity is low (0 parameters, no output schema), the description is adequate but has gaps. It covers the purpose and hints at a sequence, but without annotations or output schema, it lacks details on behavior (e.g., what 'list' returns, any side effects). For a simple listing tool, it's minimally viable but could be more complete by clarifying the output or dependencies.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% description coverage, so the schema fully documents the lack of inputs. The description doesn't need to add parameter details, and it appropriately doesn't mention any. Baseline is 4 for 0 parameters, as the description doesn't introduce confusion or redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List all available API endpoints') and the resource ('API endpoints'), making the purpose immediately understandable. It distinguishes itself from siblings like 'fetch_swagger_info' by specifying it operates 'after fetching Swagger documentation', though it doesn't explicitly contrast with all siblings like 'get_endpoint_details'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by mentioning 'after fetching Swagger documentation', suggesting a prerequisite or sequence, but it doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_endpoint_details' or 'execute_api_request'. No exclusions or clear alternatives are stated, leaving usage context somewhat vague.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_api_responseB

Validate an API response against the schema from Swagger documentation

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesThe endpoint path
methodYesThe HTTP method
statusCodeYesThe HTTP status code
responseBodyYesThe response body to validate

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool validates responses but doesn't explain how validation works (e.g., returns validation errors, success/failure status), what happens on failure, or any side effects. For a validation tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 parameters, validation logic) and lack of annotations or output schema, the description is minimally adequate. It covers the basic purpose but fails to provide critical context like validation outcomes, error handling, or integration with sibling tools, leaving gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, clearly documenting all four parameters (path, method, statusCode, responseBody). The description adds no additional parameter semantics beyond what the schema provides, such as format examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Validate an API response against the schema from Swagger documentation'. It specifies the verb 'validate' and the resource 'API response', making it understandable. However, it doesn't explicitly differentiate from sibling tools like 'execute_api_request' or 'fetch_swagger_info', which might handle related but distinct operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing Swagger documentation loaded), context (e.g., after an API call), or exclusions. With siblings like 'execute_api_request' and 'fetch_swagger_info', this lack of differentiation leaves usage ambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 5 tool updates
    • First observedexecute_api_request
    • First observedfetch_swagger_info
    • First observedget_endpoint_details
    • First observedlist_endpoints
    • First observedvalidate_api_response
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: fetching documentation, listing endpoints, getting endpoint details, executing requests, and validating responses. The descriptions make it easy to tell them apart, as they target different stages of the API workflow.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (e.g., fetch_swagger_info, list_endpoints, execute_api_request). The naming is predictable and readable throughout, with no deviations in style or convention.

Tool Count5/5

With 5 tools, the server is well-scoped for its purpose of interacting with Swagger/OpenAPI documentation and APIs. Each tool earns its place by covering distinct aspects of the workflow, from discovery to execution and validation.

Completeness5/5

The tool set provides complete coverage for the domain: it supports fetching documentation, listing and detailing endpoints, executing requests, and validating responses. There are no obvious gaps, and agents can handle the full API lifecycle without dead ends.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Vizioz/Swagger-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server