B
bkraad47/ramen
Self-hosted, multi-zone MCP server platform for GKE, EKS and AKS. A git repo of Python tools becomes canary-deployed, autoscaled Rust + Python workers with NeMo guardrails per tool, Entra ID / Google Workspace SSO, custom roles, OAuth 2.1, secrets, IP rules and audit. Clients on macOS, Windows and Linux.
SECURITY.md ✓
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
远端端点（Claude Desktop / Cursor / Windsurf 共用 mcpServers）
{
"mcpServers": {
"bkraad47-ramen": {
"url": "https://{ramen_edge}/mcp"
}
}
}把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据，我们没有替你安装或托管它。 官方 Registry 记录：这个端点列了【必填】请求头 ramen-group（Ramen group to route to）。用它要带上你自己的凭据。
VS Code（.vscode/mcp.json —— 键名是 servers，远程要 type: http）
{
"servers": {
"bkraad47-ramen": {
"type": "http",
"url": "https://{ramen_edge}/mcp"
}
}
}VS Code 的配置文件和另外三家不同：顶层键是 <code>servers</code>，远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code（命令行）
claude mcp add --transport http bkraad47-ramen https://{ramen_edge}/mcpClaude Code 不收 JSON 文件，用这条命令直接加。
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"bkraad47-ramen": {
"command": "uvx",
"args": ["ramen-mcp-bridge@latest"]
}
}
}解析自我们于 2026-10-26 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"bkraad47-ramen": {
"command": "uvx",
"args": ["ramen-mcp-bridge@latest"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio bkraad47-ramen -- uvx ramen-mcp-bridge@latest
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 4 ★ · bkraad47/ramen · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-23 · 最近见到 2026-11-14 · 共见到 26 次 · 被 23 个来源列出
- 评分构成
- 综合分 2,300 · 4 ★ · 23 个来源 · mcp
- 安装
uvx ramen-mcp-bridge@latest
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
uvx ramen-mcp-bridge@latest。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
bkraad47/ramen；我们收录于 2026-10-23；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。Build your MCP tools in Python, deploy them across zones on GKE, EKS and AKS .
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Rust MCP node + Python 3.12 runtime workers, Streamable HTTP at the edge and gRPC inside, guardrails per tool,
Entra ID and Google Workspace sign-in, autoscaling — managed from one FastAPI console.
Docs: https://bkraad47.github.io/ramen/ · Get started · How it works · The MCP repo · Connect a client with OAuth · Deploy on GCP · AWS · Azure · Contracts · Releases
> Streamable HTTP is the front door. Every worker serves POST /mcp — a URL and a bearer header, nothing to
> install — next to the gRPC service it has had since 0.3.1, on the same port, through the same guards. The stdio
> bridge stays for clients that only speak stdio.
Status. Current release 0.8.0, verified live on GKE, EKS and AKS on 2026-10-17 — smoke, the 63-check release suite
and six load-test scenarios on each cloud — then torn down; CI proves both transports on Linux and Windows. The single
record of what each run covered, and what is tested only, is
Transport → What is verified.
Build and deploy your own MCP tools across zones. Ramen turns a git repo of tools, resources and prompts
into a fleet of MCP workers behind a cloud load balancer, and keeps who-can-call-what, secrets, guardrails, canary
gates and the audit trail in one console. It is a platform for your tools, not a gateway in front of someone else's.
Each worker pairs a Rust MCP node (Streamable HTTP and gRPC on one port, bearer auth, IP allow-lists, health,
logs) with a Python 3.12 runtime that pip-installs and runs your code: user code never runs in the process that
holds the keys. The shape, the data model and why each piece is where it is:
How it works.
Git → bucket → worker. Deploy syncs the repo to a bucket; workers load by content hash. No git creds on pods.
Canary by default, gated. Roll a canary, smoke-test tools/list, diff its tool schemas against stable
(breaking changes stop unless you say breaking: true), run the repo's golden cases, then roll stable. Failure
leaves stable untouched.
Multi-zone from day one. Group → Environment → Zone → Worker; the load balancer routes on ramen-group /
ramen-zone, so one client config works for every zone.
Guardrails inside the worker. Opt a tool into a check before the call and after the result, run in the Python
runtime next to it: NVIDIA NeMo Guardrails rails (deterministic or
LLM-backed, your model and key) or a policy.py of your own. A blocked call is a readable tool error and the access
log names the rail. Fail-closed by default.
Your identity provider decides, your admins override. Add Microsoft Entra ID, Google Workspace or any OIDC
provider on the Config page, on any cloud; read a person's groups from Graph or Cloud Identity at sign-in, map them
to roles per group, and keep what admins set by hand.
Roles per group, and roles you define. Group Admin, Viewer, MCP User or a custom role on one of those bases
(analyst on Viewer), usable in memberships, provider rules and per-tool access; a role can be OAuth only.
Decide per environment who may see and who may call each tool; a drift signal flags a caller repeating one call.
Autoscaling by Ramen. Each zone runs between 1 worker and a max that admins set; the console scales up fast
Entra ID and Google Workspace sign-in, autoscaling — managed from one FastAPI console.
Docs: https://bkraad47.github.io/ramen/ · Get started · How it works · The MCP repo · Connect a client with OAuth · Deploy on GCP · AWS · Azure · Contracts · Releases
> Streamable HTTP is the front door. Every worker serves POST /mcp — a URL and a bearer header, nothing to
> install — next to the gRPC service it has had since 0.3.1, on the same port, through the same guards. The stdio
> bridge stays for clients that only speak stdio.
Status. Current release 0.8.0, verified live on GKE, EKS and AKS on 2026-10-17 — smoke, the 63-check release suite
and six load-test scenarios on each cloud — then torn down; CI proves both transports on Linux and Windows. The single
record of what each run covered, and what is tested only, is
Transport → What is verified.
Build and deploy your own MCP tools across zones. Ramen turns a git repo of tools, resources and prompts
into a fleet of MCP workers behind a cloud load balancer, and keeps who-can-call-what, secrets, guardrails, canary
gates and the audit trail in one console. It is a platform for your tools, not a gateway in front of someone else's.
Each worker pairs a Rust MCP node (Streamable HTTP and gRPC on one port, bearer auth, IP allow-lists, health,
logs) with a Python 3.12 runtime that pip-installs and runs your code: user code never runs in the process that
holds the keys. The shape, the data model and why each piece is where it is:
How it works.
Git → bucket → worker. Deploy syncs the repo to a bucket; workers load by content hash. No git creds on pods.
Canary by default, gated. Roll a canary, smoke-test tools/list, diff its tool schemas against stable
(breaking changes stop unless you say breaking: true), run the repo's golden cases, then roll stable. Failure
leaves stable untouched.
Multi-zone from day one. Group → Environment → Zone → Worker; the load balancer routes on ramen-group /
ramen-zone, so one client config works for every zone.
Guardrails inside the worker. Opt a tool into a check before the call and after the result, run in the Python
runtime next to it: NVIDIA NeMo Guardrails rails (deterministic or
LLM-backed, your model and key) or a policy.py of your own. A blocked call is a readable tool error and the access
log names the rail. Fail-closed by default.
Your identity provider decides, your admins override. Add Microsoft Entra ID, Google Workspace or any OIDC
provider on the Config page, on any cloud; read a person's groups from Graph or Cloud Identity at sign-in, map them
to roles per group, and keep what admins set by hand.
Roles per group, and roles you define. Group Admin, Viewer, MCP User or a custom role on one of those bases
(analyst on Viewer), usable in memberships, provider rules and per-tool access; a role can be OAuth only.
Decide per environment who may see and who may call each tool; a drift signal flags a caller repeating one call.
Autoscaling by Ramen. Each zone runs between 1 worker and a max that admins set; the console scales up fast
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/bkraad47-ramen/)
- 来源
- awesome · https://github.com/bkraad47/ramen
- 按领域浏览
- MCP 服务
- Traction
- 4 ★
- 收录来源
- 23 个独立来源
- 收录于
- 今天
- 安全策略
- 该仓库根目录有
SECURITY.md（我们只核文件存在，未核内容）
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。