MCP Gateway

Created By
IBMa year ago
A Model Context Protocol (MCP) Gateway. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE).
Overview

What is MCP Gateway?

MCP Gateway is a flexible, FastAPI-based gateway for the Model Context Protocol (MCP) that serves as a central management point for tools, resources, and prompts accessible by MCP-compatible LLM applications.

How to use MCP Gateway?

To use MCP Gateway, you can run it using Docker or manually install it in a Python environment. Configuration is done via environment variables or a .env file, and you can interact with it through its Admin UI or API endpoints.

Key features of MCP Gateway?

  • Centralizes tool, resource, and prompt registries while preserving MCP protocol.
  • Federates multiple MCP servers into one unified endpoint.
  • Virtualizes non-MCP services as managed MCP servers.
  • Adapts REST APIs into MCP tools with input validation and retry policies.
  • Provides a rich Admin UI for management and observability.

Use cases of MCP Gateway?

  1. Managing multiple LLM tools and resources in a unified interface.
  2. Integrating various REST APIs into a single MCP-compliant service.
  3. Facilitating communication between different LLM applications and services.

FAQ from MCP Gateway?

  • Can MCP Gateway handle non-MCP services?

Yes! It can wrap any REST API as a managed MCP server.

  • Is there a user interface for managing tools and resources?

Yes! MCP Gateway includes a rich Admin UI for easy management.

  • How do I deploy MCP Gateway?

You can deploy it using Docker or manually install it in a Python environment.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
IBM
Star
77
Language
Python
License
Apache-2.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

8 hours ago