Artificial Analysis MCP server for AI agents

Let Claude, ChatGPT or your own agent read Artificial Analysis: 1 typed function through one MCP server. No Artificial Analysis API key needed.

Functions
1
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Artificial Analysis

An MCP server for Artificial Analysis alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.

https://api.bowmark.ai/mcp/site/artificialanalysis_ai
Every site

One MCP server for Artificial Analysis and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.

Functions

Open a function to see its arguments, what it returns and how to call it.

Read 1
  • getEvaluationReturns Artificial Analysis's public AutomationBench-AA model leaderboard, including each model's score, provider, token prices and output speed.

    Arguments

    NameTypeRequired
    evaluationstringNo

    Returns ArtificialAnalysisEvaluationRow[]

    interface ArtificialAnalysisEvaluationRow {
      model: string;
      provider: string | null;
      score: number;
      inputPricePerMillionTokens: number | null;
      outputPricePerMillionTokens: number | null;
      outputTokensPerSecond: number | null;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/artificialanalysis_ai/getEvaluation

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.artificialanalysis_ai.getEvaluation();

Use it from code