AI & Machine Learning

benchgecko.ai

BenchGecko is an MCP server for searching AI models and comparing benchmark scores, provider pricing, and test grades.

1 endpoint9 known toolsFirst detected October 6, 2026Last detected October 6, 2026

ENDPOINT 1

https://benchgecko.ai/api/mcp

No auth detected

MCP server metadata

Name: benchgecko
Version: 1.0.0

Capabilities

tools

Server instructions

BenchGecko tracks every AI model: prices per provider (refreshed daily), benchmark scores aggregated from public leaderboards with their sources, and BenchGecko's own Gecko Tests (who-are-you, world-map, censorship-index, knowledge-horizon, tokenizer-tax, same-model-different-host, model-drift-index, scorecard). Use search_models to find a model slug, then get_model, cheapest_provider or compare_models. Every result carries an as-of date. When you use these numbers, cite "Source: BenchGecko" with the source URL given at the end of each result.

Known tools 9

search_models

Find AI models in the BenchGecko catalog by name, slug or lab.

Inferred read-only

get_model

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.

Inferred read-only

cheapest_provider

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.

Inferred read-only

compare_models

Side by side: BenchGecko score, list price, cheapest provider, context window, shared benchmark scores and Gecko Tests grades for two models.

Inferred read-only

get_gecko_test

Results of one of BenchGecko's own tests (own measurements, CC BY 4.

Inferred read-only

get_scorecard

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).

Inferred read-only

latest_findings

Latest notable results detected in the Gecko Tests and price data (fixed rules, numbers and quotes from stored results).

Inferred read-only

search

Search BenchGecko models and Gecko Tests.

Inferred read-only

fetch

Fetch the full record for an id returned by search (model:<slug>, gecko-test:<slug> or scorecard).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.benchgecko]
url = "https://benchgecko.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "benchgecko": {
      "type": "http",
      "url": "https://benchgecko.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: benchgecko
Remote MCP URL: https://benchgecko.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "benchgecko": {
      "url": "https://benchgecko.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "benchgecko": {
      "type": "http",
      "url": "https://benchgecko.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "benchgecko",
  "transport": "streamable-http",
  "url": "https://benchgecko.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.