mcp-gateway-registry

MCP数据服务

提供方 agentic-community · 包名 mcp-gateway-registry

数据服务 stdio · 本地进程 OAuth 授权 社区 / 第三方 Claude DesktopCursorClineClaude Code
查看接入方式

Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified ac

一句话选型结论

按资料字段整理

mcp-gateway-registry 属于数据服务类 MCP 服务器,stdio · 本地进程,OAuth 授权,可直接接入 Claude Desktop、Cursor、Cline 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类数据服务 传输方式stdio · 本地进程 鉴权OAuth 授权 部署方式本地部署
GitHub 星标 577 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

数据服务
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

mcp-gateway-registry a2a agentic-ai agents ans

支持客户端

适用场景

mcp-gateway-registrya2aagentic-ai

安装与配置

stdio · 本地进程 OAuth 授权
客户端在本机拉起子进程,数据不出本机
pip install mcp-gateway-registry

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
数据库查询

用自然语言查库、取数,不用手写 SQL。

数据同步与清洗

把多来源数据拉到一处做整理。

报表取数

按口径快速拉出统计结果。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Cursor、Cline,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在数据服务场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
mcp-gateway-registry当前 未标注 stdio · 本地进程 本地部署 有 2026-04-12
Memory 9d25f64e 9 未标注 未标注 无 2026-05-17
Getzep MCP 9 stdio · 本地进程 本地部署 有 2026-05-17
anything-llm 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Prisma MCP Server 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Astr Bot 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

数据服务
字段来自项目仓库与公开索引,中文说明由本站标注
提供方agentic-community上游标注的维护方 agentic-community
分类数据服务本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时mcp-gateway-registry · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-04-12上游最后核验时间

详细介绍

14.3 KB
来自项目仓库与上游目录的原文,未做删改

Unified Agent & MCP Server Registry – Gateway for AI Development Tools


The MCP Gateway & Registry is a single, governed control plane for every AI asset in your organization, from MCP servers and AI agents to skills and any custom asset your teams build. It is open source, licensed under Apache 2.0, and runs on Kubernetes (Amazon EKS), fully managed serverless (Amazon ECS), or Docker Compose (Amazon EC2).

It began as a gateway and registry for the Model Context Protocol (MCP): one secure entry point to many MCP servers, with centralized discovery and governance. As teams started registering agents, skills, and other assets alongside their servers, it grew into a general-purpose AI asset registry on the same gateway, access-control, and audit model it started with.

Why we built this

Without a control plane, every team wires its own MCP servers and agents by hand: separate credentials in every dotfile, no shared inventory, no audit trail, and no way to discover or govern what exists. Agents can't find other agents; servers and agents live in separate registries that can't share policy.

This platform replaces that with one governed entry point for every AI asset. Register a server, agent, skill, or custom entity once; discover it by natural-language search; reach it through a single authenticated gateway that enforces access and records every call. One control plane, one access model, one audit trail, across all asset types.

Onboard third-party OAuth MCP servers, the enterprise way. Because the gateway provides per-user egress authentication, you can connect OAuth-protected SaaS MCP servers such as Slack, Atlassian, and GitHub without every user setting up network access to those services or storing credentials on their laptop. Each user connects their account once; the gateway runs the OAuth (3LO) flow, vaults the per-user token in a secrets manager, and injects it on egress. That collapses onboarding to a single, auditable choke point, so a team can adopt a new SaaS MCP server across the enterprise without per-laptop plumbing or scattered long-lived tokens.

How it works

The gateway is the data plane (a generic nginx reverse proxy: TLS, auth validation, routing to backends) and the registry is the control plane (a FastAPI service that owns the inventory, access model, and audit trail, and decides what the gateway may route to). An auth server integrates your identity provider (Keycloak, Entra ID, Okta, Auth0, Cognito, PingFederate) for OAuth2/OIDC, and MongoDB / DocumentDB stores configuration, embeddings, sessions, and audit records.

By default, the registry handles A2A discovery, authentication, and access control, and agents then communicate directly (peer-to-peer) rather than routing every call through the gateway. For the full design and its invariants, read the Theory of the System; for layered diagrams, see Architecture Diagrams.

See it in action

Watch how MCP servers, A2A agents, and external registries work together for dynamic tool discovery:

https://github.com/user-attachments/assets/97c640db-f78b-4a6c-9662-894f975f66e2

More walkthroughs are in the demo videos.

Start here if you are a...

You are a... Start here
Decision-maker evaluating adoption Read the Executive Brief, watch the demo videos, and try the AWS Workshop.

Quick Start

The fastest path is the pre-built Docker images. Clone, set a few secrets, and run:```bash
git clone https://github.com/agentic-community/mcp-gateway-registry.git
cd mcp-gateway-registry
cp .env.example .env

Edit .env and set the required secrets (e.g. KEYCLOAK_ADMIN_PASSWORD, SECRET_KEY).

See docs/configuration.md for the full list.

nano .env

Deploy with pre-built images (pulled from Amazon ECR Public by default)

./build_and_run.sh --prebuilt

Open the Registry UI (served by nginx on port 80)

open http://localhost # macOS (Linux: xdg-open http://localhost)
```

The Complete Installation Guide has the full walkthrough for Amazon EC2 (prerequisites, MongoDB and Keycloak initialization, first user and service account, registering a server, and testing the gateway).

Deploying somewhere else?

  • Amazon ECS: see the Terraform stack README, or better, use the Terraform setup skill to have your AI coding assistant run the deployment for you.
  • Amazon EKS: see the Helm charts.
  • Just want to try it on macOS?: use the macOS setup skill to get it running on your MacBook end to end.

What's in the box

The registry holds four built-in asset types plus admin-defined custom ones, all on one control plane:

  • MCP servers: register, discover, and govern access to MCP servers behind a single authenticated gateway.
  • Agents (A2A): register agents and let them discover each other by capability; by default agent-to-agent traffic runs peer-to-peer.
  • Skills: register, version, and discover reusable SKILL.md skills, with security scanning at registration.
  • Custom entities: admins define their own schema-driven entity types (n8n workflows, policies, prompt templates, model cards, and more); see Custom Entity Types.

Across all of them you get semantic + lexical search, UI, REST, and MCP-native interfaces, and uniform governance. Key features worth calling out:

  • Use it as an AI gateway for anything HTTP: one authenticated entry point in front of model inference (OpenAI, Amazon Bedrock, any OpenAI-compatible endpoint), MCP servers, A2A agents, and any generic REST endpoint. Callers hold a gateway token; the backend URL and its credential stay in the registry, encrypted at rest and injected at egress, with per-entity streaming and the same scopes, audit, and rate limits as everything else. Off by default. Design · FAQ: OpenAI and Bedrock
  • Single authenticated gateway: one entry point; OAuth against your existing IdP (Keycloak, Entra ID, Okta, Auth0, Cognito, PingFederate) with fine-grained scopes.
  • Dynamic tool discovery: agents and coding assistants find tools at runtime by natural-language semantic search, not hard-coded config.
  • Virtual MCP servers: aggregate tools from many backends behind one endpoint, with per-tool access control.
  • Per-user egress auth (3LO / OBO / PAT): the gateway brokers third-party SaaS credentials so tokens never live on a user's laptop.
  • Security scanning + fail-closed admission gate: every registered server, agent, and skill is scanned; unsafe items are held for review.
  • External-registry federation: pull in Anthropic's MCP Registry, AWS Agent Registry, and peer registries for one unified surface.
  • Audit logging: a full, attributable audit trail of access and admin events, with credential masking, for compliance and incident review.
  • Observability: OpenTelemetry metrics and health monitoring built in.

What's New

  • Embeddings Without LiteLLM, Extra Request Headers, and Long Entries That Get Indexed - Remote embeddings no longer go through LiteLLM: the registry calls OpenAI and any OpenAI-compatible endpoint, Azure OpenAI, and Amazon Titan and Cohere on Amazon Bedrock with about 500 lines of its own code, sends the same requests so stored vectors stay valid, and rejects a model name it cannot serve at startup instead of on the first call. Operators can add up to five headers to every embeddings request for an endpoint behind an API gateway, and set the request timeout and retry count. An entry whose text is longer than the model accepts, typically a server with many tools, used to stay out of semantic search; the registry now retries a failed embedding once with the longest tool descriptions shortened and every name kept. Entra deployments now recover group memberships from Microsoft Graph when a token omits them. Every image we build also drops the two root CAs distrusted on 2026-10-20. See embeddings and the 1.34.0 release notes, which list the three model-name forms that now stop startup.
  • Virtual-Server Credential Brokering and Root-Endpoint Routing - A virtual MCP server can now front a backing server that needs a per-user credential: the backend hop goes through the same vend-and-inject step a direct call uses, keyed on the resolved backing path, so two backing servers with different credential modes can sit behind one virtual server and each gets its own vend. The caller must hold a grant on both the virtual server and the backing server, checked against the exact rewritten request, and the caller's own gateway token is never forwarded to a registrant-controlled backend. The same change lets a virtual server front a stateless Streamable HTTP backend. Separately, a server registered with append_mcp_path: false is now reachable at the bare path it advertises, instead of only the trailing-slash form MCP clients refuse to follow a redirect to. 1.33.0 release notes
  • Forward-Proxy Egress for Networks With No Direct Internet Access - A registry whose only outbound path is a corporate forward proxy could not reach any external MCP server, and on 1.31.0 could not complete a browser sign-in either. Both came from one cause: httpx wires environment-proxy support only into its own default transport, and the SSRF-guarded clients and the pooled login client each supply a custom one, so HTTP_PROXY and HTTPS_PROXY were silently ignored. EGRESS_FORWARD_PROXY_ENABLED=true now routes both through the configured proxy, with the decision coming from DNS classification rather than an operator list: a target is proxied only when every address it resolves to is public, so in-cluster servers keep their IP pin with no configuration. Resolution and classification still run in full before any CONNECT, so the cloud credential, metadata, link-local, reserved and multicast denials still execute, and a request carrying a secret accepts only https so the credential rides inside the tunnel. The cost is stated rather than buried: for a proxied public target, IP-rebind pinning is dropped, since a CONNECT tunnel takes its TLS hostname from the request URL. EGRESS_FORWARD_PROXY_CA_BUNDLE covers a TLS-intercepting proxy, loading the bundle on top of the default roots rather than replacing them. Enabling the flag refuses to start unless NO_PROXY excludes the cloud credential endpoints, because HTTP_PROXY also re-points the AWS SDK. Off by default. 1.32.0 release notes · FAQ: configuring a forward proxy · Operator guide
  • Backend Identity, Tool-Level Security, and a Faster Hot Path - Onboarding an MCP server that demands OAuth before it answers initialize no longer means parking a static bearer token on the record, where it served health checks, tool discovery, and security scanning alike with no way to scope it to discovery. Those are headless calls with no user behind them, so the registry had nothing else to present. One resolver picks at most one credential from three tiers: a machine client_credentials grant, a per-user OAuth 2.1 identity that an owner consents to once and the registry borrows from the vault, or the gateway's app-only token for obo_exchange servers. A person's own credential and the borrowed identity share a principal, a provider, and a server, so purpose forms part of the vault address and the codec binds it into the AEAD, which keeps the two apart even under a write-capable attacker. A borrowed identity lists tools and never calls one: tools/call never reaches the registry's Python, because nginx proxies it with the caller's own header. A scanner-flagged tool now carries its own block, so one false positive no longer costs the other tools on that server. A block beats admin and wildcard grants, reconciles on rescan so a stale block can clear, and hides the tool from every read projection. Search grades relevance where it used to return a flat 1.0, and in-app latency fell from 641ms to 86ms. Egress calls reuse pooled HTTP clients keyed on the SSRF-validated IP, which keeps pooling rebind-safe. 1.31.0 release notes · Authentication · OBO token exchange
    Older highlights → Feature & Release Highlights · full per-version detail in the release notes and on the GitHub Releases page.

Roadmap

The roadmap is best tracked on the GitHub Milestones page. Per-user egress auth (3LO and OBO) and A2A traffic routing shipped in 1.27.0, the gateway for any HTTP resource in 1.30.0, and backend OAuth identity plus per-tool blocking in 1.31.0. At a high level, the big features we're working on next are:

  • Keycloak RFC 8693 token exchange for OBO (1.32.0): standards-based on-behalf-of exchange for Keycloak deployments, which today cannot use the OBO egress path or backend discovery because Keycloak binds the token audience with a server-side mapper rather than a request scope.
  • Client ID Metadata Documents for coding assistants: the registry publishes its own CIMD as of 1.31.0, currently shipping disabled. Next is the identity-provider side, so an assistant connects with the least friction across providers without a pre-registered client ID.
  • Registry Copilot: an embedded chat and agent-builder experience for discovering assets and composing agents from inside the registry. Tracked as #744; not yet scheduled to a release.

Have a feature request? Please open a GitHub issue, we build in the open.

Documentation

Full documentation is on the documentation site, and every guide also lives in the docs/ folder. Stuck or have a question? Start with the FAQ / Troubleshooting guide: it covers the most common setup, auth, deployment, and registration issues.

High-traffic pages by audience:

Get started

Platform & security

Architecture & development

Design decisions
- Architecture Decision Records (ADRs) · ADR 0001: No server-side DCR

Telemetry

The registry collects anonymous, non-sensitive usage telemetry (version, OS, cloud provider, aggregate asset counts) to understand adoption. It is opt-out and on by default; no PII, credentials, endpoints, or model names are ever sent. Disable everything with MCP_TELEMETRY_DISABLED=1. Full schema and privacy guarantees: Telemetry Documentation.

Community

  • GitHub Discussions, feature requests and general discussion
  • GitHub Issues, bug reports and feature requests
  • Roadmap (GitHub Milestones), upcoming releases and their issues
  • Contributing Guide · Code of Conduct · Security Policy

Star History

View the full interactive star-growth chart at star-history.com.

License

Licensed under the Apache-2.0 License. See LICENSE for details.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
mcp-gateway-registry 怎么安装?

在客户端按下面的安装命令接入:pip install mcp-gateway-registry。对应的包名是 mcp-gateway-registry。装完在客户端配置里引用同一个包或端点。

mcp-gateway-registry 怎么在 Claude Desktop、Cursor、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

mcp-gateway-registry 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

mcp-gateway-registry 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

mcp-gateway-registry 支持哪些客户端?

资料标注支持 Claude Desktop、Cursor、Cline、Claude Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

mcp-gateway-registry 能提供哪些能力?

资料显示能力标签包括 mcp-gateway-registry、a2a、agentic-ai、agents、ans。具体工具清单以官方文档为准。

mcp-gateway-registry 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

mcp-gateway-registry 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-04-12。