Skip to content

AgentKernel AI model data

by agentkernel.si · remote · no sign-in to list tools · v1.0.0 · published by si.agentkernel

Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

Changes · 3
CompareRegistry entry

6 tools: 3 change things and 3 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 models https://www.agentkernel.si/mcp

Tools

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

6 tools

Changes things 3Claude Code: ask
  • best_for_taskRanks AI models for one task by performance only (price shown, never used for the rank).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Ranks AI models for one task by performance only (price shown, never used for the rank). Tasks cover text, coding, agents, websites/UI/games/data viz, image generation and editing, video from text or image, video editing, text to speech, transcription, music and embeddings.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • cheaper_alternativeFor a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • estimate_costMonthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
Only reads 3Claude Code: allow
  • find_modelsSearches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.No findings

    Why it is in this group

    • The name "find_models" says "find": a word for reading.
    Description, as the server wrote it
    Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • get_modelPrice, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.No findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.
    Description, as the server wrote it
    Price, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • idempotentHint: true
  • recommend_modelsReturns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional priva…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
    Returns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional privacy and licence requirements.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: 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 models https://www.agentkernel.si/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__models__recommend_models",
      "mcp__models__get_model",
      "mcp__models__find_models"
    ],
    "ask": [
      "mcp__models__best_for_task",
      "mcp__models__estimate_cost",
      "mcp__models__cheaper_alternative"
    ],
    "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 models. Review it before you use it.