RG

rayenbabdallah/getmcp

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

10 stars 2 forks Качество 59 Тренд 22Apache-2.0

Zero Trust for AI agents. Generates and protects MCP servers for both internal copilots and customer-facing agents. Apache 2.0, self-hosted.

Обзор

GetMCP Zero Trust for AI agents. Generates the MCP servers your customers' agents need, then enforces who can do what — per request, per agent, per tenant. Quickstart → · Threat model · Operations · Changelog Point GetMCP at any OpenAPI spec. It generates two runnable MCP servers (Internal "god mode" and External "customer-safe"), then runs in front of them as a policy proxy with a tamper-evident audit log. Self-hosted, Apache 2.0, no telemetry. A that sits between AI agents (Claude, ChatGPT, Cursor, your bots) and your existing API. 1. Internal + External MCP servers from any OpenAPI spec, so your customers' AI agents can safely call your API. 2. Zero Trust on every call — per-agent identity, 5 policy rule types, Slack-mediated approval for sensitive mutations, and a tamper-evident audit log you can verify with one HTTP request. : B2B SaaS companies whose customers are starting to wire AI agents into their APIs and need a Zero Trust layer they can self-host.

README

Показан фрагмент оригинального README. Открыть оригинал.


TL;DR. Point GetMCP at any OpenAPI spec. It generates two runnable MCP servers (Internal “god mode” and External “customer-safe”), then runs in front of them as a policy proxy with a tamper-evident audit log. Self-hosted, Apache 2.0, no telemetry.

What is GetMCP?

A policy proxy + audit log that sits between AI agents (Claude, ChatGPT, Cursor, your bots) and your existing API.

It does two things:

  1. Generates Internal + External MCP servers from any OpenAPI spec, so your customers’ AI agents can safely call your API.
  2. Enforces Zero Trust on every call — per-agent identity, 5 policy rule types, Slack-mediated approval for sensitive mutations, and a tamper-evident audit log you can verify with one HTTP request.
   ┌─────────┐     ┌──────────────────────────────┐     ┌──────────┐
   │  AI     │ ──► │ GetMCP — auth · policy ·     │ ──► │ Your API │
   │  agent  │     │ approval · audit · stream    │     │          │
   └─────────┘     └──────────────────────────────┘     └──────────┘

Built for: B2B SaaS companies whose customers are starting to wire AI agents into their APIs and need a Zero Trust layer they can self-host.

Not built for: routing internal traffic between microservices (use a service mesh) or rate-limiting public APIs (use a CDN / WAF). GetMCP is specifically the AI-agent → enterprise-API path.

Why not roll your own?

You’d need to build What GetMCP gives you on day 1
Auth + per-tenant isolation, with regression tests proving Org A can’t read Org B Apache-2.0, working, tested
Открыть полный README на GitHub

Установка

This server does not publish a one-line install command.

Open the repository installation guide Новичок в MCP? Начните с руководства на mcpskill.org →