G
gagarin-cloud/mcp
The gagarin MCP server — deploy and operate applications on gagarin from any MCP-speaking agent.
no SECURITY.md
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Remote endpoint (mcpServers - Claude Desktop / Cursor / Windsurf)
{
"mcpServers": {
"gagarin-cloud-mcp": {
"url": "https://mcp.gagarin.cloud/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 lists no request headers. That is not the same as key-free - the project docs decide.
VS Code (.vscode/mcp.json - the key is servers, remote needs type: http)
{
"servers": {
"gagarin-cloud-mcp": {
"type": "http",
"url": "https://mcp.gagarin.cloud/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 gagarin-cloud-mcp https://mcp.gagarin.cloud/mcp
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 0 ★ · gagarin-cloud/mcp · 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 · 23 sources · mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
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
gagarin-cloud/mcp;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.# mcp
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
mcp.gagarin.cloud — deploy with ease, maintain without fear.
Add one URL to your agent and it can run your app at a live HTTPS address, give
it Postgres, Qdrant, Valkey, a queue or a bucket, wire what may reach what, and
roll back. Alerts, logs, backups and project memory come with it, and nothing is
deleted without your approval by email. It is Gagarin's API, as tools: 50 of
them, every one annotated so a client knows which to ask you about first.
Building and pushing an image needs docker and the source, so that one step is
gg ship on the machine that has them; everything after it is here.
https://mcp.gagarin.cloud/mcp
The Model Context Protocol is how an agent finds and calls a tool it was not
built with. This is Gagarin's, and it exists so that adding Gagarin to a coding
agent is a URL rather than an install — the one artefact that makes the platform
installable rather than merely documented.
Two ways in, one implementation:
| remote | https://mcp.gagarin.cloud/mcp, streamable HTTP, credential in the Authorization header — put there by OAuth sign-in or by hand |
| local | npm run stdio from a clone of this repository, credential from GAGARINTOKEN or the file gg login wrote — for developing on this server, not a way to install it |
## Signing in
Remote, with OAuth. Give the client the URL and nothing else:
https://mcp.gagarin.cloud/mcp
Claude, ChatGPT and Claude Code prompt for sign-in when they connect: the client
opens a browser and the human signs in with GitHub or Google. A request with no
credential answers 401 with a WWW-Authenticate header pointing at
/.well-known/oauth-protected-resource/mcp, which names api.gagarin.cloud as
the authorization server. This server decides nothing about a token itself; the
engine does, on every call. GAGARINMCPORIGIN and GAGARINISSUER override the two public
names for a development setup; they are separate from GAGARINAPI, which in
the cluster is the in-cluster Service and no address a client could sign in at.
Remote, with a credential in a header. For a client that cannot sign in
over OAuth, or a machine that should not: a credential from gg login or
gg creds create.
jsonc
"mcpServers": {
"gagarin": {
"type": "http",
"url": "https://mcp.gagarin.cloud/mcp",
"headers": { "Authorization": "Bearer " }
Local, over stdio. npm run stdio from a clone runs the same tools over a
pipe, reading the file gg login wrote, or GAGARINTOKEN if it is set. It is
here to develop against, and is deliberately not published to npm: the point of
this server is that adding Gagarin to an agent is a URL and not an install, and
a package on somebody's laptop is a second copy of src/tools.ts that goes
stale the day a tool changes.
A credential that has expired or been revoked is caught at the door too, because
a client signs in again only on an HTTP 401: every POST asks the engine
/v1/whoami with the caller's token first, and the engine's 401 becomes a 401
with error="invalidtoken". One extra in-cluster call per request, and no
cache — a remembered token is a stored token, and this server stores none. Any
other failure there (the engine unreachable, a 5xx) is not a sign-in problem, so
the request goes on and each tool reports it with the engine's own code.
Add one URL to your agent and it can run your app at a live HTTPS address, give
it Postgres, Qdrant, Valkey, a queue or a bucket, wire what may reach what, and
roll back. Alerts, logs, backups and project memory come with it, and nothing is
deleted without your approval by email. It is Gagarin's API, as tools: 50 of
them, every one annotated so a client knows which to ask you about first.
Building and pushing an image needs docker and the source, so that one step is
gg ship on the machine that has them; everything after it is here.
https://mcp.gagarin.cloud/mcp
The Model Context Protocol is how an agent finds and calls a tool it was not
built with. This is Gagarin's, and it exists so that adding Gagarin to a coding
agent is a URL rather than an install — the one artefact that makes the platform
installable rather than merely documented.
Two ways in, one implementation:
| remote | https://mcp.gagarin.cloud/mcp, streamable HTTP, credential in the Authorization header — put there by OAuth sign-in or by hand |
| local | npm run stdio from a clone of this repository, credential from GAGARINTOKEN or the file gg login wrote — for developing on this server, not a way to install it |
## Signing in
Remote, with OAuth. Give the client the URL and nothing else:
https://mcp.gagarin.cloud/mcp
Claude, ChatGPT and Claude Code prompt for sign-in when they connect: the client
opens a browser and the human signs in with GitHub or Google. A request with no
credential answers 401 with a WWW-Authenticate header pointing at
/.well-known/oauth-protected-resource/mcp, which names api.gagarin.cloud as
the authorization server. This server decides nothing about a token itself; the
engine does, on every call. GAGARINMCPORIGIN and GAGARINISSUER override the two public
names for a development setup; they are separate from GAGARINAPI, which in
the cluster is the in-cluster Service and no address a client could sign in at.
Remote, with a credential in a header. For a client that cannot sign in
over OAuth, or a machine that should not: a credential from gg login or
gg creds create.
jsonc
"mcpServers": {
"gagarin": {
"type": "http",
"url": "https://mcp.gagarin.cloud/mcp",
"headers": { "Authorization": "Bearer " }
Local, over stdio. npm run stdio from a clone runs the same tools over a
pipe, reading the file gg login wrote, or GAGARINTOKEN if it is set. It is
here to develop against, and is deliberately not published to npm: the point of
this server is that adding Gagarin to an agent is a URL and not an install, and
a package on somebody's laptop is a second copy of src/tools.ts that goes
stale the day a tool changes.
A credential that has expired or been revoked is caught at the door too, because
a client signs in again only on an HTTP 401: every POST asks the engine
/v1/whoami with the caller's token first, and the engine's 401 becomes a 401
with error="invalidtoken". One extra in-cluster call per request, and no
cache — a remembered token is a stored token, and this server stores none. Any
other failure there (the engine unreachable, a 5xx) is not a sign-in problem, so
the request goes on and each tool reports it with the engine's own code.
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/gagarin-cloud-mcp/)
- Source
- awesome · https://github.com/gagarin-cloud/mcp
- Browse by field
- MCP servers
- Listed by
- 23 independent sources
- added
- today
- Security policy
- no
SECURITY.mdat the repository root (which does not mean it is unsafe)
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.