エージェントを強化
公開元自身のコマンドです。PlugMCP のエンドポイントではありません。
キーとログ付きでコピーをホスト。
npx -y [email protected]Claude Code にはローカルコマンド用のインストールリンクがありません。下のコマンドをコピーして、ターミナルで実行してください。
claude mcp add hubris-mcp -- npx -y hubris-mcp@0.2.0ターミナルで実行します。
{ "mcpServers": { "hubris-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
リモート URL か、手元のマシンのコマンドか 2 つのインストール方法の違い
PlugMCP で実行
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動公開元より
Model Context Protocol server for — an OpenAI-compatible LLM gateway with billing in rubles. Connect Claude Desktop, Claude Code, Cline, Cursor or any other MCP client to a single hosted server and get access to the model catalog, account balance and spending, and every kind of model in it: text, embeddings, rerankers, decision models, images, speech, transcription, video and YouTube transcripts.
MCP server for Hubris — an OpenAI-compatible LLM gateway billed in rubles. Catalogue, balance, spending and every kind of model — text, embeddings, rerank, images, speech, transcription, video — over stdio.
There are two ways in: connect your client straight to the hosted endpoint, or run the stdio server in this repository, which declares the same tools locally and forwards calls to that endpoint. The second is what you want for clients that speak stdio only, and for sandboxes that build from a Dockerfile.
Listing the tools needs no credential; only calling one does. With HUBRIS_API_KEY set, the stdio server takes the tool list live from the hosted endpoint, so it never lags behind new tools; without a key it serves the list bundled with the package.
https://api.hubris.pw/mcpsk-gw-..., create one at hubris.pw/keys)compare-models {task} — ready-made prompt for comparing models for a given task.npm install && npm run build
HUBRIS_API_KEY=sk-gw-... node dist/index.js
Or with Docker:
docker build -t hubris-mcp .
docker run -i --rm -e HUBRIS_API_KEY=sk-gw-... hubris-mcp
In an MCP client config:
{
"mcpServers": {
"hubris": {
"command": "node",
"args": ["/path/to/hubris-mcp/dist/index.js"],
"env": { "HUBRIS_API_KEY": "sk-gw-..." }
}
}
}
HUBRIS_MCP_URL overrides the endpoint if you need to point it elsewhere.
claude mcp add --transport http hubris https://api.hubris.pw/mcp \
--header "Authorization: Bearer sk-gw-..."
Claude Desktop only speaks stdio, so remote HTTP servers go through the mcp-remote shim. Add to claude_desktop_config.json:
{
"mcpServers": {
"hubris": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.hubris.pw/mcp",
"--transport",
"http-only",
"--header",
"Authorization:${AUTH_TOKEN}"
],
"env": {
"AUTH_TOKEN": "Bearer sk-gw-..."
}
}
}
}
Any MCP client with Streamable HTTP transport support:
Full connection guide (with client-specific caveats): hubris.pw/docs/integrations/mcp.
The Bearer key grants access to your account balance. We recommend creating a dedicated key for MCP at hubris.pw/keys so it can be revoked independently of other integrations.
Hubris is an OpenAI-compatible LLM gateway for the Russian market — one API key, one ruble-denominated balance, 400+ models. hubris.pw
MCP server for Hubris — an OpenAI-compatible LLM gateway billed in rubles. Catalogue, balance, spending and every kind of model — text, embeddings, rerank, images, speech, transcription, video — over
{ "mcpServers": { "hubris-mcp": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}概要
MCP server for Hubris — an OpenAI-compatible LLM gateway billed in rubles. Catalogue, balance, spending and every kind of model — text, embeddings, rerank, images, speech, transcription, video — over stdio.
ツール
ツール一覧はまだありません。リモートサーバーは、最初のヘルスチェック後に取得されます。
よくある質問
このページで Cursor、Claude Desktop、Claude Code、VS Code 用の stdio 設定をコピーできます。PlugMCP のプロキシではなく、公開元のインストール方法を使います。
このレコードに必須の環境変数は記載されていません。
Hubris は stdio 経由でローカル実行されます。
最終チェックは 2026-11-15 です。 MCP server for Hubris — an OpenAI-compatible LLM gateway billed in rubles. Catalogue, balance, spending and every kind of model — text, embeddings, rerank, images, speech, transcription, video — over stdio.