MCP App Store
by KeenEthics
Artificial Analysis icon

Artificial Analysis MCP Server for ChatGPT

By Artificial Analysis

Overview

Artificial Analysis independently benchmarks models and the API providers that serve them. Connect it to answer questions with current measurements instead of what a model remembers from training. Language models: the Artificial Analysis Intelligence Index and its evaluations, coding and agentic indexes, context window, price per million tokens, and output speed and time to first token measured across providers. API providers: compare how each provider serves a model on speed, latency and price, with performance over time. Media models: arena rankings for text-to-image, image editing, text-to-video, image-to-video, text-to-speech, speech-to-text, speech-to-speech and music. Every tool is read-only. Sign in with your Artificial Analysis account and choose an organization. Calls count against that organization's API quota, and the data you see follows its plan.

How to connect

  1. ChatGPT: Open the Artificial Analysis listing in the ChatGPT app directory and choose Connect. ChatGPT listing Artificial Analysis exposes 16 tools here.

Tools

aa_api_context

ChatGPT
Read API-wide context from the live API contract: purpose, attribution, plans, rate limits and data conventions. Returns documentation only and uses no quota.

aa_describe_endpoint

ChatGPT
Read the documented query parameters and response shape for the API path behind a data tool. Returns documentation only, calls no data endpoint and uses no quota. Schema refs come back as { $ref: "Name" } for aa_describe_schema.

aa_describe_fields

ChatGPT
Explain response fields for the API path behind a data tool: type, nullability, format, enum and meaning. Returns documentation only and uses no quota. With no fields, describes the top-level fields.

aa_describe_schema

ChatGPT
Read the shape of a named response schema, such as ModelDataExternal. Returns documentation only and uses no quota. Nested refs stay as { $ref: "Name" } for follow-up calls.

aa_language_model

ChatGPT
Get one language model by slug, with every evaluation score, price and performance metric. Slugs come from the model lists. Needs a Pro plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_model_performance

ChatGPT
Get a language model's output speed and latency over time, in 7, 30 or 90 day windows. Needs a Commercial plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_models

ChatGPT
List language models with every evaluation score, blended prices, context window and performance percentiles. Paginated: pass query.page, and query.prompt_type to choose the prompt length measured. Needs a Pro plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_models_free

ChatGPT
List language models with their headline Artificial Analysis indexes, input and output token prices, and median output speed and time to first token. Works on every plan. Paginated: pass query.page and use fields to keep pages small. Read-only.

aa_language_provider

ChatGPT
Get one API provider by slug, with price and performance for every model it serves. Needs a Commercial plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_provider_measurements

ChatGPT
Get an API provider's raw benchmark measurements. Access is approved per organization. Needs a Commercial plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_provider_performance

ChatGPT
Get an API provider's output speed and latency over time, in 7, 30 or 90 day windows. Needs a Commercial plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_language_providers

ChatGPT
List API providers with the language models each serves, their prices and median performance. Needs a Commercial plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_media_rankings

ChatGPT
Get Artificial Analysis Arena rankings for one media modality with rank, sample counts, pricing and release dates. Image and video modalities take query.include_categories; music takes query.include_genres. Needs a Pro plan; on a lower plan it returns 403 and still uses quota. Read-only.

aa_media_rankings_free

ChatGPT
Get Artificial Analysis Arena rankings for one media modality: each model's identity, Elo rating and confidence interval. Works on every plan. Read-only.

artificial_analysis_help

ChatGPT
Show how to use the Artificial Analysis tools, and which plan each data tool needs.

submit_feedback

ChatGPT
Send the Artificial Analysis team a report about these tools: a misleading description, a wrong or missing field, an error, or data you needed and could not get. Show your user the report first and send it only if they agree. Leave out secrets, personal data and your user's private code or prompts.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/artificial-analysis"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/artificial-analysis)