Skip to content
Models Agree logo

Models Agree MCP server

Which servers in the official MCP registry are Models Agree's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-21

← Back to Models Agree

Whose server it is
  • Registry namecom.modelsagree/modelsagreeverified in the MCP registry

The registry name sits under modelsagree.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools5
  • Server calls itselfmodelsagree
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 29 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-21
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer82 ms
  • Space in an agent's context≈ 485 tokensthe definitions of all its tools (5), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers5 tools · read 2026-10-21
  • search_best

    Find what AI models agree is the best product/tool/service for a need, or look up how a specific brand ranks. Returns matching categories and brands with a dated one-sentence verdict and source URLs. Use for any 'best X for Y' question…

  • get_best_in_category

    Get the full ranked leaderboard and verdict for a category slug (obtained from search_best or list_categories), e.g. 'best-llm-observability'.

  • get_product

    Get a single brand/product's record across every category it is ranked in, with verdicts and its homepage.

  • get_poll_history

    Get the raw poll history — every model's pick over time — behind a category's verdict. The credibility/audit trail. Optionally filter by model.

  • list_categories

    List every category ModelsAgree ranks (slug + title). Large; prefer search_best when you have a specific need.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

claude mcp add --transport http modelsagree https://modelsagree.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://modelsagree.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.