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 ✓
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
- Copy the command above
- Paste it as one entry under
mcpServersinclaude_desktop_config.json— local servers take command + args (example: clients) - Restart your client
Remote endpoint (mcpServers - Claude Desktop / Cursor / Windsurf)
{
"mcpServers": {
"bkraad47-ramen": {
"url": "https://{ramen_edge}/mcp"
}
}
}Paste this into the mcpServers config of Claude Desktop or Cursor. The endpoint comes from public evidence; we do not install or host it. Official Registry record: this endpoint declares a required request header ramen-group (Ramen group to route to). Using it means bringing your own credentials.
VS Code (.vscode/mcp.json - the key is servers, remote needs type: http)
{
"servers": {
"bkraad47-ramen": {
"type": "http",
"url": "https://{ramen_edge}/mcp"
}
}
}VS Code differs from the other three: the top-level key is <code>servers</code> and a remote endpoint also needs <code>"type": "http"</code>. Paste into .vscode/mcp.json.
Claude Code (command line)
claude mcp add --transport http bkraad47-ramen https://{ramen_edge}/mcpClaude Code does not read a config file; add the server with this command.
Client config (built from the install command this repo gives)
{
"mcpServers": {
"bkraad47-ramen": {
"command": "uvx",
"args": ["ramen-mcp-bridge@latest"]
}
}
}Parsed from the README we fetched on 2026-10-26; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"bkraad47-ramen": {
"command": "uvx",
"args": ["ramen-mcp-bridge@latest"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio bkraad47-ramen -- uvx ramen-mcp-bridge@latest
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 4 ★ · bkraad47/ramen · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- collected from the punkpeye/awesome-mcp-servers list · type: MCP server
- Harvest history
- first seen 2026-10-23 · last seen 2026-11-14 · seen 26× · listed by 23 sources
- Score
- score 2,300 · 4 ★ · 23 sources · mcp
- Install
uvx ramen-mcp-bridge@latest
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
uvx ramen-mcp-bridge@latest. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
bkraad47/ramen；first catalogued 2026-10-23；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.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
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/bkraad47-ramen/)
- Source
- awesome · https://github.com/bkraad47/ramen
- Browse by field
- MCP servers
- Traction
- 4 ★
- Listed by
- 23 independent sources
- added
- today
- Security policy
- the repository has
SECURITY.mdat its root (we checked that the file exists, not what it says)
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.