MCPgee
MCPgee
MCPgeeMCPgee

Gatekit

v1.0.0•Developer Tools•stable

A hackable Model Context Protocol (MCP) gateway

gatekitmcpai-integration
Share:
41
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Gatekit?

Gatekit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to hackable model context protocol (mcp) gateway

A hackable Model Context Protocol (MCP) gateway

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A hackable Model Context Protocol (MCP) gateway

Use Cases

Create a hackable Model Context Protocol gateway.
gatekit-ai

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMar 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gatekit

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Gatekit

Gatekit is a hackable MCP gateway that acts as a middleware layer sitting between your MCP client and any number of backend MCP servers. Instead of connecting AI tools directly to your client, Gatekit intercepts all traffic and applies configurable plugins for security (PII and secrets filtering, prompt injection detection), auditing (structured JSON/CSV/plain-text logs, token usage tracking), and tool management (renaming, filtering, custom descriptions). It supports stdio and HTTP/SSE servers, auto-detects popular MCP clients like Claude Desktop and Cursor, and can sandbox child servers using OS-native isolation.

Prerequisites

  • Python 3.10 or later on macOS, Linux, or Windows
  • pipx, uv, or pip for installation
  • At least one downstream MCP server you want to proxy through Gatekit
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Install Gatekit

Install Gatekit using your preferred Python package manager. pipx or uv are recommended to keep it isolated.

pipx install gatekit
# or
uv tool install gatekit
# or
pip install gatekit
2

Launch the terminal UI to set up your configuration

Run the Gatekit TUI to interactively configure downstream servers and plugins. Gatekit auto-detects installed MCP clients and their config locations.

gatekit
3

Create a gatekit.yaml configuration file

Define your downstream MCP servers and which plugins to apply. Below is a minimal example enabling the secrets filter and JSON-lines audit log.

servers:
  my-server:
    command: npx
    args: ["-y", "@some/mcp-server"]

plugins:
  - type: secrets_filter
  - type: audit_log
    format: jsonl
    path: /tmp/gatekit-audit.jsonl
4

Configure your MCP client to use Gatekit

Point your MCP client at the Gatekit gateway instead of the downstream server directly. Gatekit will proxy all traffic through its plugin pipeline.

{
  "mcpServers": {
    "gatekit": {
      "command": "gatekit-gateway",
      "args": ["--config", "/absolute/path/to/gatekit.yaml"]
    }
  }
}
5

Restart your MCP client

Fully quit and reopen your MCP client (e.g. Claude Desktop) to apply the new configuration. All tool calls will now flow through Gatekit's middleware pipeline.

Gatekit Examples

Client configuration

claude_desktop_config.json entry that routes all MCP traffic through Gatekit with a config file.

{
  "mcpServers": {
    "gatekit": {
      "command": "gatekit-gateway",
      "args": ["--config", "/absolute/path/to/gatekit.yaml"]
    }
  }
}

Prompts to try

Gatekit is transparent to end-users — the same prompts you would send to the underlying servers work unchanged. These examples assume downstream servers are configured.

- "Search GitHub for repositories matching 'mcp server'"
- "Read the file /home/user/notes.txt" (passes through to a filesystem server)
- "What tools are available?" (Gatekit exposes the merged tool list from all downstream servers)
- "Show me the token usage summary from the last session"

Troubleshooting Gatekit

'gatekit-gateway' command not found after installation

Ensure the pipx or uv bin directory is on your PATH. Run 'pipx ensurepath' or add ~/.local/bin (Linux/Mac) to your PATH, then open a new terminal session.

Downstream MCP server tools are not appearing in the client

Check that the 'servers' block in gatekit.yaml uses correct command/args for each downstream server. Run 'gatekit' TUI to verify connectivity, and check the audit log for any connection errors.

PII or secrets filter is blocking legitimate tool calls

Review the plugin configuration in gatekit.yaml to adjust the regex patterns used by the pii_filter and secrets_filter plugins. You can add exclusion patterns or disable specific detectors per-plugin.

Frequently Asked Questions about Gatekit

What is Gatekit?

Gatekit is a Model Context Protocol (MCP) server that hackable model context protocol (mcp) gateway It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Gatekit?

Follow the installation instructions on the Gatekit GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Gatekit?

Gatekit works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Gatekit free to use?

Yes, Gatekit is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Gatekit Alternatives — Similar Developer Tools Servers

Looking for alternatives to Gatekit? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "gatekit": { "command": "npx", "args": ["-y", "gatekit"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Gatekit?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides