# BenchGecko

Delivers daily token pricing across providers, GPU rental rates, and verified AI corporate statistics straight to your coding agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: BenchGecko
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/BenchGecko/datasets
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/benchgecko

## What it does

The server connects your agent to BenchGecko daily datasets. It updates every day. The feed supplies list prices per million tokens across input, output, and cache reads, alongside provider context limits and quantization levels.

Beyond token costs, the data tracks AI company financials from SEC filings, attention metrics, and hourly GPU prices from Vast.ai. The integration runs over HTTP via `https://benchgecko.ai/api/mcp`. It requires an active internet connection.

External benchmark leaderboards are absent. The server only returns BenchGecko's own test runs, such as coordinate scoring and host verification.

## Requirements
- Remote server: `https://benchgecko.ai/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http benchgecko https://benchgecko.ai/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add benchgecko --url https://benchgecko.ai/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "benchgecko": {
            "url": "https://benchgecko.ai/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "benchgecko": {
            "type": "http",
            "url": "https://benchgecko.ai/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http benchgecko https://benchgecko.ai/api/mcp
```

## When to use it
- compare token prices across model hosting providers
- track hourly GPU rental rates before reserving compute
- lookup verified funding, revenue, and headcount for AI labs
- monitor developer attention metrics across GitHub and Hacker News

## Example prompts
- What is the lowest output token rate for Llama 3 across available providers right now?
- Check the median hourly rental cost for an H100 according to Vast.ai metrics.
- Pull the latest funding and revenue numbers for Anthropic from SEC filings.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md