Provides a proxy for the GitHub API, allowing AI agents to access GitHub endpoints as MCP tools with integrated caching, rate limiting, and retry logic.
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 Gateway Show me the gateway statistics and current cache usage"
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.
A unified local API gateway with caching, rate limiting, and full MCP (Model Context Protocol) compatibility.
🔌 Unified API Aggregation - Manage multiple API endpoints through a single gateway
💾 Multi-Strategy Caching - LRU, LFU, FIFO, and TTL cache eviction policies
⚡ Rate Limiting - Token bucket and sliding window algorithms
🔗 MCP Protocol - Full Model Context Protocol support for AI agent integration
📊 Observability - Built-in statistics and metrics
🔄 Retry Logic - Automatic retry with exponential backoff
Related MCP server: MCP Gateway
# Clone the repository
git clone https://github.com/bandageok/mcp-api-gateway.git
cd mcp-api-gateway
# Install dependencies
pip install -r requirements.txt
# Or install directly
pip install aiohttp pyyamlpython gateway.py --create-configThis creates a config.yaml with sample endpoints:
host: localhost
port: 8080
cache:
enabled: true
max_size: 1000
ttl: 300
strategy: lru
rate_limit:
enabled: true
requests_per_minute: 60
apis:
- name: github-api
url: https://api.github.com
method: GET# With config file
python gateway.py -c config.yaml
# Or with command line arguments
python gateway.py --host 0.0.0.0 --port 8080# Call an API endpoint
curl http://localhost:8080/api/github-api/users/bandageok
# Check health
curl http://localhost:8080/health
# Get statistics
curl http://localhost:8080/stats
# Clear cache
curl -X DELETE http://localhost:8080/cache/clear
# Get configuration
curl http://localhost:8080/configThe gateway provides full MCP protocol support for AI agents:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list",
"params": {}
}Response:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"tools": [
{
"name": "github-api",
"description": "Call GET https://api.github.com",
"inputSchema": {
"type": "object",
"properties": {
"params": {"type": "object"},
"data": {"type": "object"}
}
}
}
]
}
}{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "github-api",
"arguments": {
"params": {"path": "/users/bandageok"}
}
}
}{
"jsonrpc": "2.0",
"id": 3,
"method": "resources/list",
"params": {}
}Option | Type | Default | Description |
| string | localhost | Host to bind to |
| int | 8080 | Port to bind to |
| bool | false | Enable debug mode |
| string | INFO | Logging level |
| bool | true | Enable caching |
| int | 1000 | Maximum cache entries |
| int | 300 | Cache TTL in seconds |
| string | lru | Cache strategy (lru/lfu/fifo/ttl) |
| bool | true | Enable rate limiting |
| int | 60 | Rate limit threshold |
Endpoint | Method | Description |
| GET | Health check |
| GET | Detailed health status |
| GET | Gateway statistics |
| GET | Current configuration |
| DELETE | Clear the cache |
| * | Proxy to configured API |
| POST | MCP protocol endpoint |
┌─────────────────────────────────────────────────────────────┐
│ MCP API Gateway │
├─────────────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌─────────────┐ ┌───────────────┐ │
│ │ Cache │ │Rate Limiter │ │ MCP Handler │ │
│ │ (LRU/LFU) │ │ (Token) │ │ │ │
│ └─────────────┘ └─────────────┘ └───────────────┘ │
├─────────────────────────────────────────────────────────────┤
│ API Client Pool │
├─────────────────────────────────────────────────────────────┤
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ GitHub │ │ Weather │ │ Stocks │ │ Custom │ │
│ │ API │ │ API │ │ API │ │ API │ │
│ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │
└─────────────────────────────────────────────────────────────┘Connect AI agents to external APIs through MCP:
import requests
# Initialize MCP
response = requests.post("http://localhost:8080/mcp", json={
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {}
})
# List available tools
response = requests.post("http://localhost:8080/mcp", json={
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list",
"params": {}
})Protect external APIs from being overwhelmed:
rate_limit:
enabled: true
requests_per_minute: 60 # Max 60 requests per minuteCache expensive API responses:
cache:
enabled: true
max_size: 1000
ttl: 300 # Cache for 5 minutes
strategy: lru # Evict least recently usedimport aiohttp
import asyncio
async def call_gateway():
async with aiohttp.ClientSession() as session:
# Call an API
async with session.get("http://localhost:8080/api/github-api/users/bandageok") as resp:
data = await resp.json()
print(data)
# Check stats
async with session.get("http://localhost:8080/stats") as resp:
stats = await resp.json()
print(f"Cache hit rate: {stats['cache_hit_rate']}")
asyncio.run(call_gateway())apis:
- name: my-api
url: https://api.example.com
method: GET
headers:
Authorization: Bearer YOUR_TOKEN
timeout: 30
retry_count: 3Throughput: ~1000 requests/second (with caching)
Latency: <10ms overhead (cache hit), <100ms overhead (cache miss)
Memory: ~50MB base + cache size
MIT License - See LICENSE for details.
BandageOK - GitHub
Contributions are welcome! Please feel free to submit a Pull Request.
⭐ Star us on GitHub if you find this useful!
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
One PAT, any MCP agent: Vercel, GitHub, Cloudflare, Supabase, GCP — unified dev infra gateway.
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bandageok/mcp-api-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server