What runtime or dependencies are required?
MCP Gateway runs via `uv`, requiring Python and the `uv` package manager to execute `uv run mcp-gateway`.
@Timandes
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-gateway-timandes": {
"command": "uv",
"args": [
"run",
"mcp-gateway"
]
}
}
}Tool name (Function name), which is provided to LLM.
Tool description through which LLM can understand what the tool could do.
Arguments of tool (Function arguments).
Request mapping to target HTTP API.
Response mapping for response of target HTTP API.
Boolean
HTTP method
Target HTTP API url template
HTTP headers
Header key
Header value template
Response body template
MCP Gateway is a server that translates Model Context Protocol (MCP) tool callings into traditional HTTP API requests, providing a configurable bridge to expose existing HTTP APIs through MCP.
Copy the example config file (config.example.yaml) to config.yaml, then edit it to map HTTP APIs to MCP tools. Launch the server with SSE transport using uv run mcp-gateway (default port 3001). For stdio transport, use --transport=stdio and configure it in Cursor, Cline, or MCP Inspector with command uv run mcp-gateway --transport=stdio.
{{.config.xxx}} templates--port parameterMCP Gateway runs via `uv`, requiring Python and the `uv` package manager to execute `uv run mcp-gateway`.
The server supports SSE (default, on port 3001) and stdio transport, selectable with the `--transport` parameter.
Edit the `tools` section of `config.yaml` with tool name, description, arguments, a request template (URL, method, headers), and a response template for the HTTP API response.
All configuration is stored in a local YAML file (`config.yaml`) that you create from `config.example.yaml`. No external database is used.
Yes, use Go‑template expressions like `{{.config.apiKey}}` and `{{.args.address}}` in the request template URL and headers. Static config values are defined under `server.config`.
Painless E2E Automation for Mobile and Web

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🚀 The fast, Pythonic way to build MCP servers and clients.

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments