Log inSubmit server
Hubris MCP logo

Hubris MCP

Connects MCP clients to Hubris for model discovery, account usage, and text, media, embedding, and transcription operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Hubris MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "hubris-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hubris-mcp"
      ],
      "env": {
        "HUBRIS_API_KEY": "YOUR_VALUE_HERE",
        "HUBRIS_MCP_URL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The hubris-mcp MCP server exposes Hubris’s OpenAI-compatible gateway through MCP, including model discovery, account monitoring, chat, embeddings, reranking, decisions, and media generation. It supports a hosted Streamable HTTP endpoint or a local stdio process that forwards requests to the hosted service. API credentials are needed for tool calls, while catalog listing can work without one. Reach for it when an agent needs access to Hubris models and ruble-denominated account data from an MCP-compatible client.

Use cases

  • Browse and compare Hubris models for a task
  • Monitor balance and period spending
  • Send chat, embedding, or reranking requests
  • Generate images, speech, and video
  • Transcribe audio or YouTube videos

Key features

  • Cursor-paginated model catalog
  • Model search and ruble pricing
  • Balance and usage reporting
  • Chat, embeddings, reranking, and decisions
  • Image, speech, transcription, and video tools
  • Hosted HTTP and local stdio access

Tools15

What Hubris MCP lets your agent do. Expand a tool for its parameters.

Self-reported~288 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 45d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 3d ago via OSV.dev · hubris-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit3d agoMost recent push to the default branch.
Tools exposed15Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Hubris MCP works

What hubris-mcp does

The hubris-mcp MCP server connects MCP clients to Hubris, an OpenAI-compatible gateway with ruble-denominated billing. It provides access to a catalog of active models and account information, then routes requests to models for text, embeddings, reranking, structured decisions, images, speech, transcription, and video.

The catalog tools support cursor-based listing, filtering by execution tool, capability, price, and context length, and retrieving model-specific pricing. Pricing details can include speech voices and video duration or resolution options. Account tools report the current balance and usage over a period, including request counts, tokens, and rubles spent.

How it works

The hosted service is available at https://api.hubris.pw/mcp over Streamable HTTP. Clients authenticate tool calls with a Bearer API key. The local alternative is a Node.js stdio process that declares the same tool set and forwards calls to the hosted endpoint.

The hubris-mcp MCP server also exposes a model catalog resource at hubris://catalog/models, quickstart documentation at hubris://docs/quickstart, and a finished-video resource for hosted video results. A compare-models {task} prompt is included for comparing available models against a stated task.

Setup and configuration

For a local installation, build the package with npm and start the compiled process:

Terminal
npm install && npm run build
HUBRIS_API_KEY=sk-gw-... node dist/index.js

Docker is also supported. Pass HUBRIS_API_KEY into the container when starting it. The HUBRIS_MCP_URL variable can replace the default Hubris endpoint when the process must target another URL.

A hosted connection needs the Streamable HTTP URL and an Authorization: Bearer sk-gw-... header. Claude Desktop requires an mcp-remote shim because it only speaks stdio, while clients with Streamable HTTP support can connect directly. Create a dedicated Hubris key for MCP if you want to revoke it separately from other integrations; the key grants access to account balance information.

Tools and capabilities

The hubris-mcp MCP server provides these operations:

  • Discover active models, search catalog entries, and inspect pricing.
  • Read the current balance and period-based usage totals.
  • Send chat completion, embedding, reranking, and decision requests.
  • Generate images, synthesize speech, transcribe base64-encoded audio, and start or inspect video jobs.
  • Retrieve a transcript or summary for a YouTube video.

Video generation is asynchronous: video_create starts a job, and video_get checks its status and supplies download links when available. Generated images and speech are returned as MCP image or audio content.

Limitations and notes

Listing the available tools does not require a credential, but calling them does. When HUBRIS_API_KEY is present, the stdio process obtains its tool list from the hosted endpoint; without the key, it uses the package’s bundled list, which may not include later additions.

The video content resource is available from the hosted endpoint only. Claude Desktop needs the remote transport shim, and other clients must support Streamable HTTP for a direct hosted connection. API usage can affect the Hubris account balance, so credentials should be handled as account-authorizing secrets.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Hubris MCP

hubris-mcp is an MCP server that connects MCP clients to Hubris, an OpenAI-compatible, ruble-billed LLM gateway. Its main tools cover model discovery and pricing, balance and usage, chat, embeddings, reranking, decisions, image generation, speech, transcription, video, and YouTube transcription.

Install it with npm, build it, and run the compiled stdio process with HUBRIS_API_KEY set. The documented sequence is `npm install && npm run build`, followed by `HUBRIS_API_KEY=sk-gw-... node dist/index.js`. Docker can also run the local server.

Yes, Cursor is named as a supported client. Configure it to use the hosted Streamable HTTP endpoint at `https://api.hubris.pw/mcp` with an `Authorization: Bearer sk-gw-...` header, or use the local stdio server.

Use the `mcp-remote` shim because Claude Desktop only speaks stdio. Configure the shim with the hosted Hubris MCP URL, HTTP-only transport, and an authorization token stored in the client environment.

An API key is required to call tools, but not to list them. Set `HUBRIS_API_KEY` for the local server, or provide a Bearer key when connecting directly to the hosted endpoint.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewHubris MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/hubris-mcp?style=directory)](https://allmcps.com/mcp/hubris-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/hubris-mcp"><img src="https://allmcps.com/api/badge/hubris-mcp?style=directory" alt="Hubris MCP on AllMCPs" /></a>