MCP.Market

Model Council MCP server

by ivanantigravity-lgtm·io.github.ivanantigravity-lgtm/model-council-mcp-server·v0.1.2·1 stars

Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.

B78/100grade B
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

1 stars25 downloads/wk

Reviews

Write one

Nobody has reviewed Model Council yet.

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

Model Council tools (4, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • council_model_guide

    Return a short guide on the strengths, weaknesses, and best usage of Grok, Gemini, and DeepSeek.

  • tri_model_compare

    Compare several options through three different model families.

  • tri_model_red_team

    Stress-test a plan through three different model families.

  • tri_model_scanwrite action

    Run the same task through Grok, Gemini, and DeepSeek once each and return compact JSON with raw model answers.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan7 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 158 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Model Council compares

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

Safety score
78/100
higher than 57% of 4,464 AI and agents servers
Tools
4
the typical AI and agents server has 6
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,697 AI and agents servers
Downloads a week
25
more than 11% of 1,515 AI and agents servers with a package

What its tools let an agent do: 3 read · 1 change

Install Model Council in Claude Code, Cursor or VS Code

claude mcp add model-council-mcp-server -- uvx model-council-mcp-server
Add to Cursor

What the publisher says

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

Model Council MCP Server

mcp-name: io.github.ivanantigravity-lgtm/model-council-mcp-server

MCP сервер, который прогоняет одну и ту же задачу через 3 модели параллельно и возвращает Claude их короткие ответы. Claude сам сверху делает итоговую выжимку.

Два пресета:

  • china — Moonshot Kimi, Qwen, DeepSeek
  • usa — Gemini, Grok, OpenAI

Когда вызывать

Полезно, когда:

  • задача неоднозначная
  • есть риск самоуверенного ответа одной модели
  • важны слабые места, возражения, trade-offs
  • нужно 3 разные перспективы, а не один ответ

Не надо вызывать для:

  • простого факта
  • быстрой суммаризации
  • задачи, которую решит одна нормальная модель

Что нужно для установки

  • Claude Desktop или Claude Code
  • uv
  • Python 3.11+
  • POLZAAIAPI_KEY — ключ берётся на polza.ai/dashboard/api-keys

Поставить uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

Установка за 2 минуты (через PyPI + uvx)

Claude Code / VS Code

Создай .mcp.json в корне проекта:

{
  "mcpServers": {
    "model-council": {
      "command": "uvx",
      "args": ["model-council-mcp-server@latest"],
      "env": {
        "POLZA_AI_API_KEY": "your-polza-api-key-here"
      }
    }
  }
}

Перезапусти Claude Code.

Claude Desktop (macOS)

Файл ~/Library/Application Support/Claude/claudedesktopconfig.json:

{
  "mcpServers": {
    "model-council": {
      "command": "uvx",
      "args": ["model-council-mcp-server@latest"],
      "env": {
        "POLZA_AI_API_KEY": "your-polza-api-key-here"
      }
    }
  }
}

Claude Desktop (Windows)

Файл: %APPDATA%\Claude\claudedesktopconfig.json. Содержимое идентичное.

Как проверить, что работает

После перезапуска Claude попроси:

Прогони через model council (usa) задачу: стоит ли мне добавить подписку в мой продукт?

Claude должен вызвать tool trimodelscan и вернуть 3 коротких ответа.

Tools

  • trimodelscan — 3 модели отвечают на одну задачу
  • trimodelcompare — сравнение нескольких вариантов
  • trimodelred_team — атака на идею, план или оффер
  • councilmodelguide — краткая памятка по сильным и слабым сторонам моделей

У каждого tool есть параметр preset (china или usa).

Пресеты

china

  • moonshotai/kimi-k2.5
  • qwen/qwen3.6-plus
  • deepseek/deepseek-v3.2

usa

  • google/gemini-3.1-flash-lite-preview
  • x-ai/grok-4.1-fast
  • openai/gpt-5.4-nano

Проверить актуальность ID моделей можно через GET https://polza.ai/api/v1/models/catalog. Если какая-то модель у Polza переименована — подставь свой ID через переменные окружения ниже.

Переменные окружения

Что возвращает сервер

Компактный JSON:

  • задача
  • контекст
  • 3 сырых коротких ответа от моделей
  • источники по каждой модели

Сервер заставляет модели отвечать коротко, без воды и без повтора вопроса — чтобы не раздувать контекст Claude.

Локальная разработка

git clone https://github.com/ivanantigravity-lgtm/model-council-mcp-server.git
cd model-council-mcp-server
uv sync
POLZA_AI_API_KEY=your_key uv run python -m model_council_mcp_server.server

Лицензия

MIT.

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

Model Council: common questions

Is Model Council MCP server safe?
Mostly: it is graded B (78/100). Read the Model Council safety report
How do I install Model Council?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Model Council need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Model Council maintained?
The last commit was 194 days ago (2026-04-22). The latest release is v0.1.2.
What can I use instead of Model Council?
Servers from other publishers that do the same job: llmtrim MCP server, Gemini MCP server and three.ws Avatars MCP server.
How does Model Council compare with other AI and agents MCP servers?
safety score 78/100 (higher than 57% of 4,464 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Model Council

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

  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • Gemini
    Model Context Protocol server for Google Gemini AI with chat, research, and grounding
    A
  • three.ws Avatars
    three.ws 3D avatars in your agent: render a live, interactive 3D avatar inline, or get an embed.
    A

More from ivanantigravity-lgtm →