Generate API Tools from OpenAPI Specs
Specbridge turns any OpenAPI spec dropped in a folder into ready-to-use MCP tools, with zero configuration and automatic authentication detection.
Why it matters
Automatically convert OpenAPI specifications into executable MCP tools. This asset scans a folder of specification files and generates corresponding tools without requiring additional configuration.
Outcomes
What it gets done
Scan OpenAPI specifications from a specified folder.
Generate API tools based on detected specifications.
Support for multiple authentication methods via environment variables.
Debug and list loaded specifications and tools.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-specbridge | bash Capabilities
Tools your agent gets
Get a user by ID (generated from OpenAPI specification)
Create a new user (generated from OpenAPI specification)
Overview
Specbridge MCP Server
Specbridge auto-generates MCP tools from OpenAPI specification files dropped into a folder, with automatic authentication detection from environment variables and namespace isolation so multiple APIs can coexist. Use it to give an AI assistant tool access to REST APIs that already have OpenAPI specs, without custom wrapper code. It only works for APIs with a valid OpenAPI spec - there's no tool generation without one.
What it does
Specbridge is an MCP server, built with FastMCP for TypeScript, that turns OpenAPI specifications into MCP tools automatically. It scans a folder for .json, .yaml, or .yml OpenAPI spec files and generates corresponding tools with no configuration files or separate server setup required - the filesystem is the interface. It supports namespace isolation so multiple APIs coexist cleanly (e.g. petstore_getPet, github_getUser), full OpenAPI handling of parameters, request bodies, authentication, and responses, both stdio and HTTP-streaming transports, and a built-in specbridge list command for debugging loaded specs and tools.
mkdir ~/mcp-apis
curl -o ~/mcp-apis/petstore.json https://petstore3.swagger.io/api/v3/openapi.json
specbridge --specs ~/mcp-apis
Tools are named automatically: {api_name}_{operationId} when the spec defines an operationId, or {api_name}_{method}_{path_segments} otherwise (e.g. github_get_user_repos from GET /user/repos). Authentication is auto-detected from environment variables in a .env file placed in the specs folder, using naming patterns derived from the spec's filename: {API_NAME}_API_KEY for an X-API-Key header, {API_NAME}_TOKEN or {API_NAME}_BEARER_TOKEN for a Bearer Authorization header, and {API_NAME}_USERNAME/{API_NAME}_PASSWORD for Basic Auth.
When to use - and when NOT to
Use it when you want to expose one or more existing REST APIs (that already have OpenAPI/Swagger specs) as MCP tools for an AI assistant without writing custom tool wrappers - just drop the spec files in a folder and point the server at it. It is not useful for APIs without an OpenAPI specification, since tool generation depends entirely on the spec's operations and schemas being present and valid; if no tools appear, the project's troubleshooting guidance is to run specbridge list to check for parsing errors and confirm the spec file extension is correct.
Inputs and outputs
Input is a folder of OpenAPI spec files (and an optional .env file for credentials). Output is one auto-generated MCP tool per API operation, callable by name (e.g. example_getUser, example_createUser), registered with the MCP client and ready to invoke with the parameters/request body defined in the spec.
How to install
npm install -g specbridge
Then register it in Claude Desktop or Cursor's MCP configuration, pointing --specs at your specs folder:
{
"mcpServers": {
"specbridge": {
"command": "specbridge",
"args": ["--specs", "/path/to/your/specs/folder"]
}
}
}
Or run it without a global install via npx -y specbridge --specs /absolute/path/to/your/specs. Use absolute paths without spaces for the --specs argument to avoid platform/client compatibility issues. Restart the MCP server after adding or changing spec files to reload tools.
Who it's for
Developers who want to give an AI assistant tool access to existing REST APIs with OpenAPI specs - internal services, third-party APIs like GitHub or a Petstore-style demo API - without writing and maintaining custom MCP tool code for each endpoint.
Source README
SpecBridge
An MCP server that turns OpenAPI specifications into MCP tools. Scan a folder for OpenAPI spec files and automatically generate corresponding tools. No configuration files, no separate servers - just drop specs in a folder and get tools.Built with FastMCP for TypeScript.
✨ Features
- 🎯 Zero Configuration: Filesystem is the interface - just drop OpenAPI specs in a folder
- 🔐 Auto Authentication: Simple
.envfile with{API_NAME}_API_KEYpattern - 🏷️ Namespace Isolation: Multiple APIs coexist cleanly (e.g.,
petstore_getPet,github_getUser) - 📝 Full OpenAPI Support: Handles parameters, request bodies, authentication, and responses
- 🚀 Multiple Transports: Support for stdio and HTTP streaming
- 🔍 Built-in Debugging: List command to see loaded specs and tools
🚀 Quick Start
1️⃣ Install (optional)
npm install -g specbridge
2️⃣ Create a specs folder
mkdir ~/mcp-apis
3️⃣ Add OpenAPI specs
Drop any .json, .yaml, or .yml OpenAPI specification files into your specs folder:
# Example: Download the Petstore spec
curl -o ~/mcp-apis/petstore.json https://petstore3.swagger.io/api/v3/openapi.json
4️⃣ Configure authentication (optional)
Create a .env file in your specs folder:
# ~/mcp-apis/.env
PETSTORE_API_KEY=your_api_key_here
GITHUB_TOKEN=ghp_your_github_token
OPENAI_API_KEY=sk-your_openai_key
5️⃣ Add to MCP client configuration
For Claude Desktop or Cursor, add to your MCP configuration:
If installed on your machine:
{
"mcpServers": {
"specbridge": {
"command": "specbridge",
"args": ["--specs", "/path/to/your/specs/folder"]
}
}
}
Otherwise:
{
"mcpServers": {
"specbridge": {
"command": "npx",
"args": ["-y", "specbridge", "--specs", "/absolute/path/to/your/specs"]
}
}
}
💻 CLI Usage
🚀 Start the server
# Default: stdio transport, current directory
specbridge
# Custom specs folder
specbridge --specs ~/my-api-specs
# HTTP transport mode
specbridge --transport httpStream --port 8080
📋 List loaded specs and tools
# List all loaded specifications and their tools
specbridge list
# List specs from custom folder
specbridge list --specs ~/my-api-specs
🔑 Authentication Patterns
The server automatically detects authentication from environment variables using these patterns:
| Pattern | Auth Type | Usage |
|---|---|---|
{API_NAME}_API_KEY |
🗝️ API Key | X-API-Key header |
{API_NAME}_TOKEN |
🎫 Bearer Token | Authorization: Bearer {token} |
{API_NAME}_BEARER_TOKEN |
🎫 Bearer Token | Authorization: Bearer {token} |
{API_NAME}_USERNAME + {API_NAME}_PASSWORD |
👤 Basic Auth | Authorization: Basic {base64} |
The {API_NAME} is derived from the filename of your OpenAPI spec:
petstore.json→PETSTORE_API_KEYgithub-api.yaml→GITHUB_TOKENmy_custom_api.yml→MYCUSTOMAPI_API_KEY
🏷️ Tool Naming
Tools are automatically named using this pattern:
- With operationId:
{api_name}_{operationId} - Without operationId:
{api_name}_{method}_{path_segments}
Examples:
petstore_getPetById(from operationId)github_get_user_repos(generated fromGET /user/repos)
📁 File Structure
your-project/
├── api-specs/ # Your OpenAPI specs folder
│ ├── .env # Authentication credentials
│ ├── petstore.json # OpenAPI spec files
│ ├── github.yaml #
│ └── custom-api.yml #
└── mcp-config.json # MCP client configuration
📄 Example OpenAPI Spec
Here's a minimal example that creates two tools:
# ~/mcp-apis/example.yaml
openapi: 3.0.0
info:
title: Example API
version: 1.0.0
servers:
- url: https://api.example.com
paths:
/users/{id}:
get:
operationId: getUser
summary: Get user by ID
parameters:
- name: id
in: path
required: true
schema:
type: string
responses:
'200':
description: User found
/users:
post:
operationId: createUser
summary: Create a new user
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
name:
type: string
email:
type: string
responses:
'201':
description: User created
This creates tools named:
example_getUserexample_createUser
🔧 Troubleshooting
❌ No tools appearing?
Check that your OpenAPI specs are valid:
specbridge list --specs /path/to/specsEnsure files have correct extensions (
.json,.yaml,.yml)Check the server logs for parsing errors
⚠️ Note: Specbridge works best when you use absolute paths (with no spaces) for the
--specsargument and other file paths. Relative paths or paths containing spaces may cause issues on some platforms or with some MCP clients.
🔐 Authentication not working?
- Verify your
.envfile is in the specs directory - Check the naming pattern matches your spec filename
- Use the list command to verify auth configuration:
specbridge list
🔄 Tools not updating after spec changes?
- Restart the MCP server to reload the specs
- Check file permissions
- Restart the MCP client if needed
🛠️ Development
# Clone and install
git clone https://github.com/TBosak/specbridge.git
cd specbridge
npm install
# Build
npm run build
# Test locally
npm run dev -- --specs ./examples
🤝 Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.