MCP服务器用于 artificialanalysis.ai——实时模型基准、定价、速度和提供商数据;无密钥（抓取网站自身的有效载荷），设计上是令牌高效
概览
MCP服务器 artificialanalysis.ai——实时AI模型基准、定价、速度、上下文/参数规格、服务提供商端点以及图像/视频/语音/音乐领域。AA发布的每一个基准和指数都被覆盖——排行榜套件、决策模型、多语言指数、设备基准集和评估图表分析——专为按代币付费的代理设计。 不需要API密钥。一个无密钥数据源：网站Next.js RSC飞行载荷，抓取并缓存本地——没有配额，没有后端选择，没有备份逻辑。每个响应头都显示aa：rsc。 一行，不克隆（UV会帮你取回并运行）： 向MCP客户端注册（omp、Claude代码、Codex等）： 上面的 JSON 安装了（可调用工具，公开为 mcp__aa_ ）。A 是另一种东西——代理通过 skill:// 按需读取的 markdown 指令，通过复制目录（或 npx 技能添加 ...）到技能根（如 ~/.agents/skills/ 或 /）来安装。
概述（AI 翻译）
MCP服务器 artificialanalysis.ai — 实时AI模型 基准测试、定价、速度、上下文/参数规格、提供者端点以及 图像/视频/语音/音乐领域。AA发布的每一个基准和指数都被覆盖—— 排行榜套件、决策模型、多语言索引、设备内功能 基准集和评估图分析——为按代币付费的代理人设计。
不需要API密钥。一个无密钥数据源：网站的Next.js RSC飞行载荷，
本地抓取和缓存——没有配额，没有后端选择，没有备用逻辑。
每个响应头都显示 aa:rsc。
aa:rsc |
|
|---|---|
| 来源 | 该网站Next.js RSC飞行载荷 |
| 需求 | 什么都没有 |
| 承载 | ~每款模型50项指标，包括17个跨模型基准、定价、速度、每模型任务成本分解、服务提供商端点、媒体板（包括无声视频场域）、完整语音/语音板、六个能力指数、决策模型套件、多语言指数、设备/移动基准集以及搜索API指标 |
| 配额 | 无 |
安装
一行，不克隆（UV会帮你取回并运行）：
或者一次性安装aa-mcp执行文件：
本地结账/开发：
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
aa-mcp
MCP server for artificialanalysis.ai — live AI model benchmarks, pricing, speed, context/parameter specs, provider endpoints and the image/video/speech/music arenas. Every benchmark and index AA publishes is covered — the leaderboard suite, the Decision Models, the Multilingual Index, the on-device benchmark set and the eval-chart breakdowns — shaped for agents that pay per token.
No API key needed. One keyless data source: the site’s Next.js RSC flight payloads,
scraped and cached locally — no quota, no backend selection, no fallback logic.
Every response header shows aa:rsc.
aa:rsc |
|
|---|---|
| source | the site’s Next.js RSC flight payloads |
| needs | nothing |
| carries | ~50 metrics per model incl. 17 cross-model benchmarks, pricing, speed, per-model cost-per-task breakdown, provider endpoints, media boards (incl. the silent video arenas), the full speech/voice boards, the six Capability Indexes, the Decision-Models suite, the Multilingual Index, the on-device/mobile benchmark set and the Search-API metrics |
| quota | none |
Install
One line, no clone (uv fetches and runs it for you):
uvx --from git+https://github.com/HenryGetz/aa-mcp aa-mcp
Or install the aa-mcp executable once:
uv tool install --from git+https://github.com/HenryGetz/aa-mcp aa-mcp # -> ~/.local/bin/aa-mcp
Local checkout / development:
git clone && cd aa-mcp
uv sync # creates .venv with the mcp SDK
uv run aa-mcp # serve on stdio
Register with an MCP client (omp, Claude Code, Codex, …):
{
"mcpServers": {
"aa": {
"type": "stdio",
"command": "/home/USER/.local/bin/aa-mcp",
"timeout": 120000
}
}
}
Skills and MCP install
The JSON above installs the MCP server (callable tools, exposed as
mcp__aa_). A skill is a different thing — markdown instructions an agent
reads on demand via skill://, installed by copying a directory (or
npx skills add …) into a skills root such as ~/.agents/skills/ or
/.agents/skills/; it adds no tools, and omp only notices it after a restart.
This repo ships one at skills/aa-mcp/SKILL.md.
Full commands, paths and troubleshooting for both: docs/SKILLS.md.
No MCP client? The same tools are reachable from a plain shell as aa-mcp-cli (same
install as aa-mcp; python -m aa_mcp.cli from a checkout) — e.g.
aa-mcp-cli call aa_leaderboard '{"top":3}' prints exactly what the MCP tool returns.
Tools
| tool | answers |
|---|---|
aa_leaderboard |
smartest / best / cheapest / fastest models, best value (mode=value), Pareto frontier (mode=frontier, delegates to aa_pareto), budget and capability filters |
安装
uvx --from git+https://github.com/HenryGetz/aa-mcp aa-mcp配置
{
"mcpServers": {
"aa": {
"type": "stdio",
"command": "/home/USER/.local/bin/aa-mcp",
"timeout": 120000
}
}
}