mcp-api-gateway
Allows interacting with the GitHub API, enabling operations such as managing repositories, creating issues, and user management via automatically generated tools from GitHub's Swagger specification.
Click on "Install 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., "@mcp-api-gatewaylist all pets from the Petstore API"
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.
api-gateway
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations. Point it at any Swagger/OpenAPI spec and it automatically generates tools that Claude can use.
Available on the Docker MCP Toolkit.
Quick Installation
Using Docker MCP Toolkit (Recommended)
The easiest way to get started is through the Docker MCP Toolkit, which provides one-click setup with Docker Desktop.
Using Docker Hub
Add to your claude_desktop_config.json:
{
"mcpServers": {
"my-api": {
"command": "docker",
"args": [
"run", "--rm", "-i", "--pull", "always",
"-e", "API_1_NAME=my-api",
"-e", "API_1_SWAGGER_URL=https://api.example.com/swagger.json",
"-e", "API_1_BASE_URL=https://api.example.com/v1",
"-e", "API_1_HEADER_AUTHORIZATION=Bearer YOUR_TOKEN",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Using npx
API_1_NAME=my-api \
API_1_SWAGGER_URL=https://api.example.com/swagger.json \
API_1_BASE_URL=https://api.example.com/v1 \
npx mcp-api-gatewayLocal Build
git clone https://github.com/rflpazini/mcp-api-gateway
cd mcp-api-gateway
docker build -t mcp-api-gateway .
docker run --rm -it \
-e API_1_NAME=test \
-e API_1_SWAGGER_URL=https://petstore.swagger.io/v2/swagger.json \
-e API_1_BASE_URL=https://petstore.swagger.io/v2 \
mcp-api-gatewayRelated MCP server: OpenAPI to MCP
Configuration
Core Variables
Variable | Description | Required | Default |
| Unique API name | Yes | — |
| Swagger/OpenAPI spec URL | Yes | — |
| API base URL (overrides spec) | No | From spec |
| Custom headers (e.g., | No | — |
| JSON object with multiple headers | No | — |
Performance Tuning
For large APIs with hundreds of endpoints, these variables reduce the tool list payload sent to Claude:
Variable | Description | Default |
|
|
|
|
|
|
| Comma-separated path prefixes to include (e.g., | All paths |
| Comma-separated OpenAPI tags to include (e.g., | All tags |
| Comma-separated parameter names to strip from schemas (e.g., | None |
Reliability
Variable | Description | Default |
| Request timeout in milliseconds |
|
| Max retry attempts for 429/5xx errors (exponential backoff) |
|
| Max response size in bytes before truncation |
|
Performance Results
Tested with a 925-endpoint enterprise API:
Configuration | Tools | Payload | Reduction |
No optimization | 1093 | 2,269 KB | — |
| 1093 | 633 KB | 72% |
| 53 | 184 KB | 92% |
| 94 | 50 KB | 98% |
Recommendation: Use API_N_TOOL_MODE=grouped for any API with more than 50 endpoints.
Examples
Simple API with Authentication
{
"mcpServers": {
"github-api": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "API_1_NAME=github",
"-e", "API_1_SWAGGER_URL=https://api.github.com/swagger.json",
"-e", "API_1_HEADER_AUTHORIZATION=token ghp_xxxxxxxxxxxx",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Large API with Grouped Tools
{
"mcpServers": {
"enterprise-api": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "API_1_NAME=myapi",
"-e", "API_1_SWAGGER_URL=https://api.company.com/v3/api-docs",
"-e", "API_1_BASE_URL=https://api.company.com",
"-e", "API_1_TOOL_MODE=grouped",
"-e", "API_1_SCHEMA_MODE=compact",
"-e", "API_1_HEADER_AUTHORIZATION=Bearer your_token",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Multiple APIs
Configure multiple APIs by incrementing the index (API_1_*, API_2_*, API_3_*):
{
"mcpServers": {
"company-apis": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "API_1_NAME=users",
"-e", "API_1_SWAGGER_URL=https://api.company.com/users/swagger.json",
"-e", "API_1_HEADER_X_API_KEY=users_key_123",
"-e", "API_2_NAME=products",
"-e", "API_2_SWAGGER_URL=https://api.company.com/products/openapi.yaml",
"-e", "API_2_HEADER_AUTHORIZATION=Bearer products_token",
"-e", "API_3_NAME=orders",
"-e", "API_3_SWAGGER_URL=https://api.company.com/orders/spec.json",
"-e", "API_3_HEADERS={\"Authorization\":\"Bearer token\",\"X-Tenant\":\"company123\"}",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Filtered Endpoints
Only load specific parts of a large API:
{
"mcpServers": {
"filtered-api": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "API_1_NAME=myapi",
"-e", "API_1_SWAGGER_URL=https://api.company.com/swagger.json",
"-e", "API_1_PATH_PREFIX=/api/v3/users,/api/v3/orders",
"-e", "API_1_SCHEMA_MODE=compact",
"-e", "API_1_EXCLUDE_PARAMS=_clientRegion,_platform",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Local Swagger File
Mount a local Swagger file into the container:
{
"mcpServers": {
"local-api": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/path/to/swagger.yaml:/swagger.yaml",
"-e", "API_1_NAME=local-api",
"-e", "API_1_SWAGGER_URL=file:///swagger.yaml",
"-e", "API_1_BASE_URL=http://host.docker.internal:3000",
"rflpazini/mcp-api-gateway:latest"
]
}
}
}Features
Cookie-Based Authentication
The server automatically persists cookies across requests. When an API returns Set-Cookie headers (e.g., after a login call), those cookies are stored and replayed on subsequent requests to the same API. No configuration needed.
Grouped Tools
When API_N_TOOL_MODE=grouped is set, endpoints are automatically grouped into resource tools:
Tagged APIs: Groups by OpenAPI tag (e.g., all
/usersendpoints become onemyapi_Userstool)Untagged APIs: Infers groups from path structure (e.g.,
/pets,/store)Each grouped tool lists available operations in its description, and the LLM selects which one to call via an
operationparameter
Health Check
A built-in check_api_health tool lets Claude verify API connectivity. It pings each configured API's base URL and reports reachability, HTTP status, and response time.
Retry with Backoff
Failed requests (429, 500, 502, 503, 504) are automatically retried with exponential backoff. The server honors Retry-After headers from rate-limited APIs.
Using in Claude
Available Commands
View available APIs: "What APIs are configured?"
Explore endpoints: "How do I create a user?" / "What parameters do I need?"
Execute operations: "Create a user named John with email john@email.com"
Check health: "Is the API reachable?"
Security
Best Practices
Never commit tokens: Use environment variables or secrets
Use limited scope tokens: Only necessary permissions
Rotate tokens regularly: Update your tokens periodically
Always use HTTPS: Ensure your APIs use HTTPS
Docker Image Security
The production image uses Google Distroless as the runtime base:
No shell, no package manager, no OS utilities
Runs as non-root user
0 known vulnerabilities
Node.js 24 LTS (supported until April 2028)
Troubleshooting
API not showing up
Check if the Swagger URL is accessible from the container
Confirm environment variables are correct (especially
API_N_SWAGGER_URL)Check logs:
docker logs <container_id>
Authentication error
Verify token is correct
Confirm header format (Bearer, Basic, etc)
For cookie-based auth: ensure the login endpoint is called first
Too many tools / slow startup
Use
API_N_TOOL_MODE=groupedto reduce tool countUse
API_N_PATH_PREFIXorAPI_N_TAGSto filter endpointsUse
API_N_SCHEMA_MODE=compactto reduce schema size
Request timeouts
Increase timeout:
API_N_TIMEOUT=60000Check API latency directly
Contributing
PRs are welcome! Some ideas:
OAuth authentication support
Smart response caching
WebSocket support
Web configuration interface
Metrics and observability
License
MIT License - see LICENSE file for details.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/rflpazini/mcp-api-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server