MCP Gateway
A compact non-production-ready MCP gateway that routes tool calls to configured downstream MCP servers, with a dashboard to enable or disable tools.
README
MCP Gateway

A compact non-production-ready MCP gateway.
Built with LLM-powered tools to befriend LLMs and the tools.
Use cases
- You need to expose the MCP server beyond localhost (ie for a dockerized harness)
- You want to use the MCP server, but disable some of its tools
- You need to expose the MCP, using one protocol, to a harness using other protocol
It routes (proxies) tool calls to configured downstream MCP servers.
It currently supports downstream streamable-http and sse transports.
It also has a dashboard where you can enable or disable certain tools.
Run
uv sync
cp gateway.example.json gateway.json
uv run mcp-gateway
Use the MCP Inspector or any MCP client against /http/mcp (or /sse/sse for a legacy client).
Configure upstream clients
Add http://localhost:64345/http/mcp as an endpoint to your client or harness.
Configure downstream servers
Edit gateway.json accordingly.
headers are optional and are never shown by the dashboard.
disabled_tools is optional per server. List downstream tool names (before any gateway renaming) to hide at startup.
Restart the gateway after changing this list.
Exposed tools
The gateway exposes only tools discovered from downstream servers. It copies each tool's name, description, schemas, annotations, and result without a gateway wrapper.
When two or more downstream servers expose the same tool name, every conflicting tool is exposed as
servername-toolname, for example github-search.
Tool discovery happens at gateway startup. Restart the gateway to pick up downstream inventory changes.
Disclaimer
This is a starter gateway, not an authorization boundary. Expect bugs. Never expose beyond localhost.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.