MCP.Market

Hubris MCP server

online · 82% uptime
by hubris.pw·pw.hubris/hubris-mcp·v1.1.0

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

A98/100grade A
What users say
No reviews yet
Be the first
Safety scan
A98/100

full report

Adoption
Growing

0 stars100 downloads/wk

Reviews

Write one

Nobody has reviewed Hubris yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Hubris tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-11-04 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • Live reliabilityremote reachable in 823ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 14 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10
Overall 98/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Hubris compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
98/100
higher than 99% of 4,461 AI and agents servers
Uptime
82%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
1,454 ms
faster than 5% of 2,334 AI and agents servers
Downloads a week
100
more than 63% of 1,554 AI and agents servers with a package

Install Hubris in Claude Code, Cursor or VS Code

claude mcp add --transport http hubris-mcp https://api.hubris.pw/mcp
Add to Cursor

What the publisher says

From the Hubris repository's README, as published. We do not edit it. Read it on GitHub

Hubris MCP

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 chat completions.

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.

  • Endpoint: https://api.hubris.pw/mcp
  • Transport: Streamable HTTP
  • Auth: Bearer API key (sk-gw-..., create one at hubris.pw/keys)
  • Full docs: hubris.pw/docs/integrations/mcp

Tools

Resources

Prompts

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

Run locally (stdio)

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-..." }
    }
  }
}

HUBRISMCPURL overrides the endpoint if you need to point it elsewhere.

Connect

Claude Code

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 claudedesktopconfig.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:

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

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-11-04restoreC → Ascore 98
  • 2026-11-03downgradeA → Cscore 64: Remote endpoint did not respond

Hubris: common questions

Is Hubris MCP server safe?
Yes, by our scan: it is graded A (98/100). Read the Hubris safety report
How do I install Hubris?
It runs remotely at api.hubris.pw. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Hubris need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Hubris maintained?
The last commit was 16 days ago (2026-10-20). The latest release is v1.1.0.
Is Hubris up?
82% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Hubris?
Servers from other publishers that do the same job: freellmpool MCP server, Lm MCP server and Agent-Native Chat MCP server.
How does Hubris compare with other AI and agents MCP servers?
safety score 98/100 (higher than 99% of 4,461 AI and agents servers); uptime 82% (of our recent checks; the typical remote AI and agents server answers 100%); response time 1,454 ms (faster than 5% of 2,334 AI and agents servers). Full comparison.

Alternatives to Hubris

Same job from other publishers: the closest match first, then the best rated.

  • freellmpool
    OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
    A
  • Lm
    Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • Memanto
    MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
    A
  • Alibaba Cloud DashScope — Qwen
    Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
    B