Developer · Local MCP server

Model Council

Consult other LLMs as tools - ask them, compare their answers, synthesize a conclusion.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Totti0135/model-council
Version
0.14.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-08-24
Updated
2026-08-24
Publisher
Totti0135 (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/Totti0135) · how
Repository
github.com/Totti0135/model-council
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPImodel-council-mcp0.14.0stdioCOUNCIL_MODELS, COUNCIL_CONFIG

How to connect Model Council

Model Council runs locally from a Python package published to PyPI: model-council-mcp version 0.14.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx model-council-mcp. It reads these environment variables: COUNCIL_MODELS and COUNCIL_CONFIG; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "model-council": {
      "command": "uvx",
      "args": [
        "model-council-mcp"
      ],
      "env": {
        "COUNCIL_MODELS": "<value>",
        "COUNCIL_CONFIG": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
MockHeroGenerate realistic relational test data - 156 field types, 22 locales, JSON/CSV/SQL, free previews.Remote & Local · HTTP, stdioLive check: ✗ no handshakemockhero.dev
MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.Local · HTTPOCI image (Docker): docker.io/mockserver/mockserver:8.0.0
Mockzilla MCPMock OpenAPI specs locally, or log in to deploy hosted mocks on mockzilla.org from your MCP client.Local · stdionpm: @mockzilla/mcp
Model Card Lint GpaiLints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d.Local · stdionpm: @readystack/model-card-lint-gpai
Model LedgerModel inventory and governance: trace deployed models and their dependencies as an append-only log.Local · stdioPyPI: model-ledger
Model Price RadarLLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.Local · stdioPyPI: model-price-radar-mcp
Modelbound MCPLocal-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.Local · stdionpm: modelbound-mcp
ModelcostsaverOffline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.Local · stdionpm: @workswarm/modelcostsaver