Skip to main content
Glama
Arephan

ModelsAgree

by Arephan

ModelsAgree MCP Server

What the top AI models agree is the best product, tool, or service — as an MCP server.

ModelsAgree continuously polls ChatGPT, Claude, Gemini, and Grok on "best X for Y" questions and publishes the consensus: a dated one-sentence verdict, the full ranked leaderboard, and a public audit trail of every model's pick over time. This MCP server makes that data directly callable by any MCP host.

Covers all domains except medical/health, financial/investment, and legal advice (the models hedge there).

Connect

Hosted, stateless, read-only, no auth:

https://modelsagree.com/mcp

Claude (claude.ai or Claude Desktop): Settings → Connectors → Add custom connector → paste the URL above.

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "modelsagree": { "url": "https://modelsagree.com/mcp" }
  }
}

Any MCP client that speaks Streamable HTTP works the same way.

Related MCP server: polydev-ai

Tools

Tool

Arguments

Returns

search_best

query

Categories & brands matching a need, each with a dated verdict + source URL

get_best_in_category

slug

Full ranked leaderboard + verdict for a category

get_product

slug

One brand's record across every category it's ranked in

get_poll_history

slug, model?, limit?

The per-model poll audit trail behind a verdict

list_categories

The full catalog (slug + title)

Example

Ask your assistant: "What's the best LLM observability tool?" — it calls search_best, gets best-llm-observability with the consensus verdict, then get_best_in_category for the full ranking.

Data & attribution

Rankings are re-polled on a demand-gated cadence and every response is licensed CC BY 4.0 (attribution: modelsagree.com). The underlying open API is also directly fetchable at https://modelsagree.com/api/v1/ (see /api/v1/README.md).

Powered by

A single stateless endpoint on Cloudflare Workers wrapping the public ModelsAgree API — no database of its own, no keys, no state.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Provides access to multiple frontier LLM models (GPT, Claude, Gemini, Grok, DeepSeek) for consulting a "conclave" of AI perspectives, enabling peer-ranked evaluations and synthesized consensus answers for important decisions.
    8
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Queries multiple AI models simultaneously (GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1) via a single API call to provide diverse expert perspectives and consensus recommendations.
    MIT