Skip to content

What's That Model?

by whatsthatmodel.com · remote · no sign-in to list tools · v1.0.0 · published by com.whatsthatmodel

Sourced AI video/image capabilities, explained task recommendations and verified access context.

Read only
CompareRegistry entry

8 tools: 8 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http whats-that-model https://whatsthatmodel.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Only reads 8Claude Code: allow
  • best_model_forGet an editorial shortlist for a known use case with verified constraints.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get an editorial shortlist for a known use case with verified constraints.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • compare_modelsCompare documented capabilities and task fit.No findings

    Why it is in this group

    • The name "compare_models" says "compare": a word for reading.
    Description, as the server wrote it
    Compare documented capabilities and task fit. Unknowns stay explicit.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • find_modelFind an AI model by creation task and verified constraints.No findings

    Why it is in this group

    • The name "find_model" says "find": a word for reading.
    Description, as the server wrote it
    Find an AI model by creation task and verified constraints. Editorial recommendation; not a benchmark score.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • get_modelGet model capabilities, dated citations, editorial limitations and labeled optional access link.No findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.
    Description, as the server wrote it
    Get model capabilities, dated citations, editorial limitations and labeled optional access link.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • get_prompt_tipsGet untested prompting guidance, clearly distinguished from measured outputs.No findings

    Why it is in this group

    • The name "get_prompt_tips" says "get": a word for reading.
    Description, as the server wrote it
    Get untested prompting guidance, clearly distinguished from measured outputs.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • list_modelsList curated AI models including independent non-affiliate alternatives.No findings

    Why it is in this group

    • The name "list_models" says "list": a word for reading.
    Description, as the server wrote it
    List curated AI models including independent non-affiliate alternatives.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • where_to_useReturn official and optional commercial access destinations, without guaranteeing plan entitlements.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return official and optional commercial access destinations, without guaranteeing plan entitlements.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http whats-that-model https://whatsthatmodel.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__whats-that-model__find_model",
      "mcp__whats-that-model__compare_models",
      "mcp__whats-that-model__get_model",
      "mcp__whats-that-model__best_model_for",
      "mcp__whats-that-model__list_models",
      "mcp__whats-that-model__where_to_use",
      "mcp__whats-that-model__get_trending_workflows",
      "mcp__whats-that-model__get_prompt_tips"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as whats-that-model. Review it before you use it.