Skip to content

BenchGecko

by benchgecko.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.benchgecko

AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.

Changes · 2

9 tools: 2 change things and 7 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 benchgecko https://benchgecko.ai/api/mcp

Tools

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

9 tools

Changes things 2Claude Code: ask
  • cheapest_providerEvery provider serving a model, sorted by input price per 1M tokens (refreshed daily from provider endpoints), with output price, quantization and 1 day uptime.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
    Every provider serving a model, sorted by input price per 1M tokens (refreshed daily from provider endpoints), with output price, quantization and 1 day uptime.

    Annotations the server declares

    • title: Cheapest provider for a model
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • latest_findingsLatest notable results detected in the Gecko Tests and price data (fixed rules, numbers and quotes from stored results).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
    Latest notable results detected in the Gecko Tests and price data (fixed rules, numbers and quotes from stored results).

    Annotations the server declares

    • title: Latest findings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 7Claude Code: allow
  • compare_modelsSide by side: BenchGecko score, list price, cheapest provider, context window, shared benchmark scores and Gecko Tests grades for two models.No findings

    Why it is in this group

    • The name "compare_models" says "compare": a word for reading.
    Description, as the server wrote it
    Side by side: BenchGecko score, list price, cheapest provider, context window, shared benchmark scores and Gecko Tests grades for two models.

    Annotations the server declares

    • title: Compare two models
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fetchFetch the full record for an id returned by search (model:<slug>, gecko-test:<slug> or scorecard).No findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.
    Description, as the server wrote it
    Fetch the full record for an id returned by search (model:<slug>, gecko-test:<slug> or scorecard).

    Annotations the server declares

    • title: Fetch a BenchGecko record
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_gecko_testResults of one of BenchGecko's own tests (own measurements, CC BY 4.0): who-are-you (Does the model know which lab made it?) world-map (How well does the model draw the world map f…No findings

    Why it is in this group

    • The name "get_gecko_test" says "get": a word for reading.
    Description, as the server wrote it
    Results of one of BenchGecko's own tests (own measurements, CC BY 4.0): who-are-you (Does the model know which lab made it?) world-map (How well does the model draw the world map from memory?) censorship-index (How often does the model refuse legitimate questions?) knowledge-horizon (Where does the model's knowledge of world events actually stop?) tokenizer-tax (How many more tokens does the same text cost outside English?) same-model-different-host (Do providers serving the same open model give the same quality?) model-drift-index (Do models quietly change behind the same name?)

    Annotations the server declares

    • title: Gecko Test results
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_modelCore facts for one AI model: BenchGecko score and rank, list price, price at every provider, benchmark scores with their original sources, Gecko Tests grades and as-of dates.No findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.
    Description, as the server wrote it
    Core facts for one AI model: BenchGecko score and rank, list price, price at every provider, benchmark scores with their original sources, Gecko Tests grades and as-of dates.

    Annotations the server declares

    • title: Get model facts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_scorecardBenchGecko Gecko Scorecard: every model across BenchGecko's own profile tests with a letter grade per test and an overall Gecko Score (behavior, not intelligence).No findings

    Why it is in this group

    • The name "get_scorecard" says "get": a word for reading.
    Description, as the server wrote it
    BenchGecko Gecko Scorecard: every model across BenchGecko's own profile tests with a letter grade per test and an overall Gecko Score (behavior, not intelligence).

    Annotations the server declares

    • title: Gecko Scorecard
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_modelsFind AI models in the BenchGecko catalog by name, slug or lab.No findings

    Why it is in this group

    • The name "search_models" says "search": a word for reading.
    Description, as the server wrote it
    Find AI models in the BenchGecko catalog by name, slug or lab. Returns slugs to use with get_model, cheapest_provider and compare_models, with BenchGecko score and list price.

    Annotations the server declares

    • title: Search AI models
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 benchgecko https://benchgecko.ai/api/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__benchgecko__search_models",
      "mcp__benchgecko__get_model",
      "mcp__benchgecko__compare_models",
      "mcp__benchgecko__get_gecko_test",
      "mcp__benchgecko__get_scorecard",
      "mcp__benchgecko__search",
      "mcp__benchgecko__fetch"
    ],
    "ask": [
      "mcp__benchgecko__cheapest_provider",
      "mcp__benchgecko__latest_findings"
    ],
    "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 benchgecko. Review it before you use it.