MCP Gateway

Created By
lasso-securitya year ago
A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
Overview

What is MCP Gateway?

MCP Gateway is a plugin-based gateway that orchestrates other Model Context Protocol (MCP) servers, allowing developers to build enterprise-grade agents and enhance their AI infrastructure.

How to use MCP Gateway?

To use MCP Gateway, install the package via pip and configure your mcp.json file to manage the lifecycle of MCP servers. Start the server with the appropriate guardrails enabled.

Key features of MCP Gateway?

  • Agnostic Guardrails: Configurable security filters to prevent sensitive data exposure.
  • Unified Visibility: Comprehensive dashboard for monitoring all MCPs.
  • Advanced Tracking: Detailed logs and usage analytics for optimization.

Use cases of MCP Gateway?

  1. Masking sensitive information like tokens and credentials.
  2. Centralized management of multiple MCP servers.
  3. Real-time monitoring and risk assessment of AI interactions.

FAQ from MCP Gateway?

  • Can MCP Gateway handle multiple MCP servers?

Yes! It can manage multiple MCP servers through a unified interface.

  • Is MCP Gateway secure?

Yes! It includes various guardrails to ensure data security and privacy.

  • How do I install MCP Gateway?

You can install it using the command: pip install mcp-gateway.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
lasso-security
Star
107
Language
Python
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
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)

a day ago