# MCP Gateway & Registry — Team Tool Control

> MCP Gateway & Registry centralizes MCP servers and agent tools with auth, search, and audit, so teams can manage integrations and scan servers before use.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

```bash
git clone https://github.com/agentic-community/mcp-gateway-registry.git
cd mcp-gateway-registry
cp .env.example .env

export DOCKERHUB_ORG=mcpgateway
./build_and_run.sh --prebuilt
```

Open `http://localhost:7860` (Registry UI).

## Intro

MCP Gateway & Registry centralizes MCP servers and agent tools with auth, search, and audit, so teams can manage integrations and scan servers before use.

- **Best for:** teams that want a governed registry for MCP servers with auth, scanning, and audit trails
- **Works with:** Docker/Podman; registry UI + APIs; integrates with AI coding assistants and MCP clients (per README)
- **Setup time:** 20–60 minutes

## Practical Notes

- Per README: semantic search endpoint `POST /api/search/semantic` returns relevance-scored matches across servers, tools, and agents.
- Per README: supports telemetry with opt-out via `MCP_TELEMETRY_DISABLED=1` (privacy-first, no PII per doc).
- Use it as a policy point: enforce auth, rate limits, and security scans before agents can use a server.

## Main

A pragmatic governance model:

1. **Inventory everything.** Register MCP servers with owners, environments, and trust levels.
2. **Make “approved” explicit.** Don’t let agents discover arbitrary remote servers; gate by policy.
3. **Scan + monitor.** Run scheduled scans and health checks; disable servers that regress.
4. **Keep audit trails.** When an incident happens, you need to know which agent used which tool, when, and with what auth.

If you already run Keycloak/SSO, align identities so human and machine auth are consistent across the registry and your internal services.

### FAQ

**Q: Do I need Kubernetes?**
A: No—README includes quick start with prebuilt images (Docker/Podman). Kubernetes is optional for production scaling.

**Q: What should I store as metadata?**
A: Owner, environment, data sensitivity, allowed tools, and any compliance flags (HIPAA/PCI) you care about.

**Q: How do I prevent tool sprawl?**
A: Centralize discovery in the registry, require ownership, and periodically prune unused or risky servers.

## Source & Thanks

> Source: https://github.com/agentic-community/mcp-gateway-registry
> License: Apache-2.0
> GitHub stars: 644 · forks: 166

---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/agentic-community/mcp-gateway-registry.git
cd mcp-gateway-registry
cp .env.example .env

export DOCKERHUB_ORG=mcpgateway
./build_and_run.sh --prebuilt
```

打开 `http://localhost:7860`（Registry UI）。

## 简介

MCP Gateway & Registry 用统一注册表管理 MCP servers 与 agent 工具：提供认证、语义搜索、审计与健康监控，还能在注册时做安全扫描，适合团队治理与合规。

- **适合谁：** 需要对 MCP servers 做统一治理（认证、扫描、审计）的团队
- **可搭配：** Docker/Podman；注册表 UI + APIs；可与 AI coding assistants / MCP clients 集成（见 README）
- **准备时间：** 20–60 分钟

## 实战建议

- README：语义搜索 `POST /api/search/semantic` 可跨 server/tool/agent 返回相关性结果。
- README：提供匿名遥测；可用 `MCP_TELEMETRY_DISABLED=1` 关闭（文档称不发 PII）。
- 把它当策略入口：在 agent 使用前统一做认证、限流与安全扫描。

## 主要内容

更务实的治理方式：

1. **先做资产盘点。** 给每个 MCP server 标注 owner、环境、信任等级。
2. **把“已批准”显式化。** 不要让 agent 随机发现远程 server；用策略做准入。
3. **扫描 + 监控。** 定时扫描与健康检查；出现回归就禁用或降级。
4. **保留审计链路。** 发生事故时，你需要知道哪个 agent 在什么时间用什么权限调用了什么工具。

如果你已有 Keycloak/SSO，建议统一身份体系，让人和机器的认证策略在注册表与内网服务一致。

### FAQ

**必须上 Kubernetes 吗？**
答：不必须。README 的 quick start 用 prebuilt images（Docker/Podman）；K8s 可选用于生产扩展。

**元数据应该记录什么？**
答：owner、环境、数据敏感级别、允许的工具集合，以及你关心的合规标记。

**怎么避免工具泛滥？**
答：把发现入口集中到注册表，强制 owner 责任，并周期性清理长期不用或高风险 server。

## 来源与感谢

> Source: https://github.com/agentic-community/mcp-gateway-registry
> License: Apache-2.0
> GitHub stars: 644 · forks: 166


---
Source: https://tokrepo.com/en/workflows/mcp-gateway-registry-team-tool-control
Author: MCP Hub