Hubris

pw.hubris由 hubris.pw 发布官方发布者v1.1.0更新于 Nov 2, 2026

OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.

已验证Streamable HTTP可网页运行金融媒体与设计AI 与机器学习

概览

AI 生成的概览

Hubris MCP 将助手接入 Hubris 的 OpenAI 兼容 LLM 网关：浏览 400+ 模型、查看卢布价格与余额，并执行对话、向量、图像、语音和视频调用。

可以做什么
  • 列出并搜索模型目录，按能力、价格或上下文长度筛选，查看单个模型的卢布定价
  • 查询账户余额与某段时间的消费（请求数、token、卢布）
  • 执行对话补全、生成向量、按相关性重排文档
  • 提出带概率的是非、选择与量表决策，生成图像、合成语音、转写音频
  • 启动视频生成、查询任务状态并获取下载链接，转写或摘要 YouTube 视频
  • 以资源形式读取模型目录与快速入门，并使用对比模型的提示模板
适用场景
适合希望通过一个 MCP 连接访问多种文本、向量、图像、语音和视频模型，并使用单一卢布计费账户，同时让助手在消费前后核对价格、余额和用量的场景。
运行要求
需要 Hubris 账户和 API 密钥（sk-gw-...），通过 HUBRIS_API_KEY 或 Bearer Authorization 头提供。可连接托管的 Streamable HTTP 端点，或用 Node.js（或 Docker）在本地运行 npm stdio 包。列出工具无需密钥，调用工具则需要。可用 HUBRIS_MCP_URL 覆盖端点。
安装前请注意
调用会消耗账户中以卢布计费的余额，包括图像、语音和视频生成。Bearer 密钥可访问账户余额，建议使用可单独撤销的专用密钥。提示词、音频等输入会发送到 Hubris 网关及其上游模型提供方。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Hubris，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/pw.hubris%2Fhubris-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "hubris": {
      "type": "http",
      "url": "https://api.hubris.pw/mcp"
    }
  }
}

README

Hubris MCP

[Smithery] [npm] [Hubris MCP on mcprush]

Model Context Protocol server for Hubris — 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.

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.

Tools

ToolDescription
models_listFull catalog of active models, cursor-paginated.
models_searchFilter by the tool that runs the model (tool), capability, price, context length.
models_get_pricingPricing for a specific model, in rubles; voices for speech models, durations and resolutions for video models.
balance_getCurrent account balance.
usage_getSpending over a period: requests, tokens, rubles.
chat_completeLLM chat request — same as POST /v1/chat/completions.
embeddings_createEmbedding vectors — POST /v1/embeddings.
rerankOrder documents by relevance to a query — POST /v1/rerank.
decisions_askYes/no, choice and scale answers with probabilities — POST /v1/decisions.
image_generateDraw an image, returned as image content — POST /v1/images/generations.
speech_createText to speech, returned as audio content — POST /v1/audio/speech.
transcription_createSpeech to text from base64 audio — POST /v1/audio/transcriptions.
video_createStart a video generation — POST /v1/videos.
video_getStatus of a video task; download links once it is ready — GET /v1/videos/{id}.
youtube_transcribeTranscript or summary of a YouTube video — POST /v1/video/transcriptions.

Resources

URIContent
hubris://catalog/modelsFull model catalog as a single JSON document.
hubris://docs/quickstartQuickstart page.
hubris://videos/{id}/contentA finished video, linked from video_get (hosted endpoint only).

Prompts

  • compare-models {task} — ready-made prompt for comparing models for a given task.

Run locally (stdio)

bash
npm install && npm run buildHUBRIS_API_KEY=sk-gw-... node dist/index.js

Or with Docker:

bash
docker build -t hubris-mcp .docker run -i --rm -e HUBRIS_API_KEY=sk-gw-... hubris-mcp

In an MCP client config:

json
{  "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.

Connect

Claude Code

bash
claude mcp add --transport http hubris https://api.hubris.pw/mcp \  --header "Authorization: Bearer sk-gw-..."

Claude Desktop

Claude Desktop only speaks stdio, so remote HTTP servers go through the mcp-remote shim. Add to claude_desktop_config.json:

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-..."      }    }  }}

Cline / Cursor / other clients

Any MCP client with Streamable HTTP transport support:

FieldValue
TransportStreamable HTTP
URLhttps://api.hubris.pw/mcp
Auth headerAuthorization: Bearer sk-gw-...

Full connection guide (with client-specific caveats): hubris.pw/docs/integrations/mcp.

Security

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.

About Hubris

Hubris is an OpenAI-compatible LLM gateway for the Russian market — one API key, one ruble-denominated balance, 400+ models. hubris.pw

来源：README.md，提交 cbb7a73

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v1.1.0最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分