# Hubris (npm · hubris-mcp)

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

- Trust score: 74/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `api.hubris.pw`: 38/100, [markdown](https://verifymcp.io/servers/pw-hubris-hubris-mcp/api.md), [page](https://verifymcp.io/servers/pw-hubris-hubris-mcp/api)
- npm · `hubris-mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp.md), [page](https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp)

## Channel facts

- Registry: `npm`
- Package: `hubris-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1502 tokens (~300/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (80% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Hubris MCP server?

Hubris runs locally as an npm package, launched with npx -y hubris-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pw-hubris-hubris-mcp -- npx -y hubris-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "pw-hubris-hubris-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hubris-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pw-hubris-hubris-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hubris-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pw-hubris-hubris-mcp -- npx -y hubris-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pw-hubris-hubris-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "hubris-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pw-hubris-hubris-mcp --command npx --arg -y --arg hubris-mcp
```

### Hermes

```yaml
mcp_servers:
  pw-hubris-hubris-mcp:
    command: "npx"
    args: ["-y", "hubris-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "pw-hubris-hubris-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "hubris-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pw-hubris-hubris-mcp -t stdio -c npx -a -y hubris-mcp
```

### Other

```json
{
  "mcpServers": {
    "pw-hubris-hubris-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hubris-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 72, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-09 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-08 (score 53)

First indexed and scored.

## MCP tools (5)

### `models_list` (~197 tokens)

List models

Walk the whole Hubris catalogue page by page, ordered by model id. Returns every active model with its capabilities, context window and ruble price.

Use this when you need the complete catalogue — to cache it, to count models, or to scan for something no filter covers. When you are looking for a model that fits a task, use models_search instead: it filters by capability, price and context server-side and saves you a few hundred rows.

Paging: read `nextCursor` from the response and pass it back as `cursor`. When `nextCursor` is absent you have reached the end. The catalogue holds roughly 550 models, so a full walk is about 11 calls at the default page size.

Input parameters:

- `cursor` (string): The `nextCursor` value from the previous response. Omit for the first page.
- `limit` (integer): Models per page, 1–200. Defaults to 50.

Output parameters:

- `models` (array)
- `nextCursor` (string): Pass back as `cursor` to fetch the next page. Absent when the last page was returned.

### `models_search` (~398 tokens)

Search models

Find models that fit a task. Filters by name, capability, price ceiling and context window, and can sort the result. This is the tool to reach for when choosing a model — it does the filtering server-side and returns at most 50 rows.

All filters combine with AND, and every one of them is optional: calling with no arguments returns the first 50 active models.

Two things worth knowing about prices. `maxInputPer1MRub` keeps only models billed per token, because a ruble-per-million ceiling is meaningless for a model billed per image. The `cheap_input` and `cheap_output` sorts push non-token models to the end of the list for the same reason — their token rate reads as zero, which would otherwise put video models at the top of "cheapest".

Input parameters:

- `capability` (string): Keep only models with this capability. vision — reads images. image_gen — draws them. transcription — speech to text via /v1/audio/transcriptions. audio_in — accepts an audio recording in chat. audio…
- `maxInputPer1MRub` (number): Ceiling on the price of 1M input tokens, in rubles. Also restricts the result to models billed per token, since the ceiling means nothing for models billed per image or minute.
- `minContext` (integer): Keep only models whose context window is at least this many tokens.
- `query` (string): Case-insensitive substring matched against the model id and display name, e.g. "claude" or "gpt".
- `sort` (string): cheap_input / cheap_output — ascending token price, models not billed per token go last. big_context — widest context window first. popular — most used on Hubris first. Unsorted when omitted.

Output parameters:

- `models` (array): Matching models, at most 50.

### `models_get_pricing` (~136 tokens)

Get model pricing

The full price of one model in rubles — the authoritative answer to "what does this cost".

Prefer this over the pricing embedded in models_list and models_search whenever the model is not billed per token. Those two return "0.00" token rates for such models; only this tool returns `perUnit`, where the real price per image, per second or per thousand characters lives.

Errors with InvalidParams if the model id is unknown or the model is no longer active.

Input parameters:

- `modelId` (string, required): Exact model id from the catalogue, vendor included, e.g. "openai/gpt-6-astra".

Output parameters:

- `currency` (string): All prices are in rubles.
- `inputPer1MRub` (string): Price of 1M input tokens in rubles, decimal string, e.g. "182.40". "0.00" when unit is not "token".
- `isFree` (boolean): True only for genuinely free models. Do not infer this from a zero price: models billed per image or per minute also report "0.00" token rates.
- `outputPer1MRub` (string): Price of 1M output tokens in rubles, decimal string. "0.00" when unit is not "token".
- `perUnit` (array): Present only for models not billed per token. This is where their real price lives.
- `unit` (string): Billing unit. "token" — priced per token, the two Rub fields below are meaningful. "unit" — priced per image, per minute, per character and so on; token fields are "0.00" and the real price is in mod…

### `balance_get` (~102 tokens)

Get account balance

Current balance of the Hubris account the API key belongs to, in rubles.

Worth checking before a long or expensive run: requests are refused once the balance is spent. The balance can go slightly negative — one operation is allowed to overdraw it, and the next one is refused.

Two representations of the same number come back. Use `balanceKopecks` for arithmetic and comparisons — it is an exact integer string. Use `balanceRub` for display.

Output parameters:

- `balanceKopecks` (string): The same balance in kopecks as an integer string. Use this one for arithmetic: it is exact, while the ruble string is for display.
- `balanceRub` (string): Balance in rubles as a decimal string, e.g. "1240.55". Negative when the account is overdrawn.

### `chat_complete` (~433 tokens)

Chat completion

Run a chat completion on any model in the Hubris catalogue and get the answer back. Full parity with POST /v1/chat/completions — same request shape, same response shape, including tool calls, structured output and reasoning. Streaming is not available here: MCP tool calls are synchronous, and `stream` is ignored if you pass it.

This is how you reach a model you cannot reach otherwise — pick an id with models_search, then call it here. Useful for delegating a subtask to a cheaper or a stronger model than the one you are running on.

The call spends real money from the account balance: it is billed per token at the catalogue price, in rubles. balance_get shows what is left.

Input parameters:

- `max_tokens` (integer): Cap on the length of the answer, in tokens.
- `messages` (array, required): Conversation so far, oldest first.
- `model` (string, required): Model id from the catalogue, vendor included and matched exactly, e.g. "anthropic/claude-sonnet-5". Short names and names with a trailing date are rejected. Use models_search to find one.
- `reasoning`: Extended thinking on models with the "reasoning" capability: {effort:"low"|"medium"|"high"}, {max_tokens:N}, or {enabled:false} to turn it off.
- `response_format`: {type:"json_object"} or {type:"json_schema", json_schema:{…}} to constrain the answer to JSON.
- `seed` (integer): Best-effort determinism. Not every model honours it.
- `stop`: Up to four strings that cut the answer short.
- `temperature` (number): Sampling temperature, 0–2. Some newer models reject it; leave it out unless you need it.
- `tool_choice`: "auto", "none", "required", or a specific function to force.
- `tools` (array): Function-calling tools, OpenAI shape. Model must have the "tools" capability.
- `web_search`: Enables built-in web search on models whose capabilities include "web_search".

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp#diagnostics

## Score history

- 2026-09-21: 74
- 2026-09-20: 74
- 2026-09-19: 73
- 2026-09-18: 73
- 2026-09-17: 72
- 2026-09-16: 72
- 2026-09-15: 68
- 2026-09-14: 68
- 2026-09-13: 68
- 2026-09-12: 68
- 2026-09-11: 68
- 2026-09-10: 68
- 2026-09-09: 68
- 2026-09-08: 53

## Common questions

### What is the Hubris MCP server?

Hubris is an MCP server listed in the public MCP registry as pw.hubris/hubris-mcp. OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat. This page covers its npm package (hubris-mcp).

### Is the Hubris MCP server safe to use?

Hubris scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Hubris MCP server expose?

Hubris exposes 5 tools: models_list, models_search, models_get_pricing, balance_get, chat_complete. Their descriptions and schemas cost roughly 1,266 tokens of context every time the server is loaded.

### Is the Hubris MCP server still maintained?

Hubris is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Hubris MCP server under?

Hubris declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/hubris-mcp
- Socket report: https://socket.dev/npm/package/hubris-mcp
- Repository: https://github.com/Aimagine-life/hubris-mcp
- Website: https://hubris.pw/
- Changelog RSS feed: https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp.json
- HTML version of this page: https://verifymcp.io/servers/pw-hubris-hubris-mcp/hubris-mcp