Log inSubmit server
Model Council MCP Server logo

Model Council MCP Server

Routes one task to three AI models through Polza AI and returns short responses for Claude to compare.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Model Council MCP Server

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

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "model-council-mcp-server": {
      "command": "uvx",
      "args": [
        "model-council-mcp-server@latest"
      ],
      "env": {
        "POLZA_AI_API_KEY": "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 model-council-mcp-server MCP server sends one task to three models in parallel through Polza AI and returns their short answers to Claude. It supports China and USA presets, each selecting three configured models, plus tools for scanning, comparison, red-teaming, and model guidance. Responses include the task, context, raw model answers, and source identifiers in compact JSON. Reach for it when a decision needs multiple perspectives, objections, or trade-off analysis rather than a single straightforward answer.

Use cases

  • Evaluate several product or business options
  • Red-team a plan, offer, or idea
  • Compare independent answers to an ambiguous question
  • Review model strengths before choosing a preset

Key features

  • Parallel three-model task scans
  • China and USA model presets
  • Option comparison tool
  • Idea and plan red-teaming
  • Model strengths and weaknesses guide
  • Configurable Polza model IDs

Tools4

What Model Council MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~53 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 1d ago

Recent health check succeeded.

5/5 checks healthy over the last 35d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · model-council-mcp-server@latest (PyPI)

Adoption & maintenance

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

GitHub stars1Stargazers on the source repository.
Last commit6mo agoMost recent push to the default branch.
Tools exposed4Callable tools this server registers over MCP.

How Model Council MCP Server works

What model-council-mcp-server MCP server does

The model-council-mcp-server MCP server gives Claude access to a small panel of three language models through the Polza AI API. It submits the same task to all three models concurrently, then returns their concise responses so Claude can produce the final synthesis. The server does not provide the final analysis itself; Claude performs that higher-level summary after receiving the model outputs.

Two presets select different model groups:

  • china: Moonshot Kimi, Qwen, and DeepSeek
  • usa: Gemini, Grok, and OpenAI

The configured model IDs can be changed with environment variables if the names in the Polza catalog change.

How it works

Each tool accepts a preset value of china or usa. For a selected preset, the server sends the task to its three associated models in parallel.

The server prompts the models to stay concise, avoid repeating the question, and omit unnecessary wording. Claude can then compare the independent answers and create an overall response. This approach is intended for ambiguous decisions, evaluation of alternatives, identifying objections, and challenging an idea or plan. A single model is generally more appropriate for simple facts or quick summarization.

Tools and capabilities

Available MCP tools include:

  • tri_model_scan: asks three models to respond to the same task.
  • tri_model_compare: evaluates multiple options or variants.
  • tri_model_red_team: looks for weaknesses in an idea, plan, or offer.
  • council_model_guide: provides a short reference to the selected models’ strengths and weaknesses.

The model-council-mcp-server MCP server exposes the same two presets through each tool. The exact model used by each preset is configurable rather than fixed in application code.

Setup and configuration

The server requires Python 3.11 or newer, uv, a Claude Desktop or Claude Code installation, and a POLZA_AI_API_KEY value from the Polza API dashboard. A typical MCP configuration runs the package with uvx and passes the API key through the server’s environment.

Claude Code uses a .mcp.json file in the project root. Claude Desktop uses its platform-specific configuration file: claude_desktop_config.json under the macOS application-support directory or the Windows application-data directory. After adding the entry, restart the client and request a council scan.

For local development, clone the repository, run uv sync, and start the module with uv run python -m model_council_mcp_server.server while providing the API key.

Required configuration:

  • POLZA_AI_API_KEY

Optional settings include POLZA_BASE_URL, model-specific variables for both presets, and LOG_LEVEL. The default API endpoint is https://polza.ai/api/v1. The Polza model catalog can be queried to confirm current model IDs before overriding them.

Limitations and notes

The server depends on Polza AI access and a valid API key. Its output consists of short, unaggregated model responses; Claude is expected to perform the final synthesis. Running a council produces three model calls for each request, so it is better suited to questions where independent perspectives matter than to routine lookups or minimal-latency tasks.

The model-council-mcp-server MCP server is distributed under the MIT license.

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 Model Council MCP Server

model-council-mcp-server is an MCP server that connects Claude to three configurable models through the Polza AI API. Its main tools scan a task with three models, compare options, red-team an idea or plan, and explain model strengths and weaknesses. Results include short responses and model sources.

Install it with `uvx` in an MCP configuration and provide `POLZA_AI_API_KEY`. Claude Code uses a project `.mcp.json` file, while Claude Desktop uses its platform-specific configuration file. Restart the client after saving the configuration.

It uses three models selected by the `china` or `usa` preset. The China preset defaults to Moonshot Kimi, Qwen, and DeepSeek; the USA preset defaults to Gemini, Grok, and OpenAI. Each model ID can be overridden with an environment variable.

Yes, it supports Claude Code and Claude Desktop through standard MCP configuration files. Claude Code reads `.mcp.json` from the project root, while Claude Desktop uses its macOS or Windows application configuration path.

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 PreviewModel Council MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/model-council-mcp-server?style=directory)](https://allmcps.com/mcp/model-council-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/model-council-mcp-server"><img src="https://allmcps.com/api/badge/model-council-mcp-server?style=directory" alt="Model Council MCP Server on AllMCPs" /></a>