Hello, AI

com.helloaiPublished by helloai.comOfficial publisherv1.0.0Updated Oct 29, 2026

Ask your assistant which frontier model to use and get a live, Elo-backed answer.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

A remote MCP server that lets an assistant look up and rank six frontier AI models by Elo, price, context and use case.

What you can do
  • Rank tracked models for a task such as coding, reasoning, overall or daily use, with optional cost, context and provider filters
  • List every tracked model with Elo and its provenance, prices per million tokens, context window, strengths and description
  • Fetch one model's full record by id or exact name
  • List curated use-case categories with their hand-set leader and a short insight
  • Read recent Hello, AI articles with title, date, category, excerpt and URL
  • Check data freshness, app version, model and article counts, scoring version, snapshot fingerprint and rate limit
When to use it
Useful when you want an assistant to suggest which frontier model fits a task, compare list prices and context windows, or cite current model rankings and articles instead of relying on its training data.
Requirements
A remote streamable HTTP endpoint; no package, environment variable or header is declared. No authentication is declared, so no account or API key appears to be needed.
Before you install
Scores are an ordering aid, not a quality measure, and are only comparable between calls sharing the same scoring version, snapshot and matched category. Models without a usable Elo are never ranked, and category leaders are hand-set labels rather than Elo-derived. Data is refreshed weekly, so check freshness before relying on it.

Installation

In SourceWeft

  1. Open Hello, AI in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.helloai%2Fdirectory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "hello-ai": {
      "type": "http",
      "url": "https://helloai.com/mcp"
    }
  }
}

Tools

6

recommend_models

Recommend models for a task

Rank Hello, AI's tracked frontier models for a task. Same scoring as GET /api/recommend: task match 40%, Elo 35%, input cost 15%, context 10% (Elo 55%, cost 25%, context 20% when no task matches). Only rated models rank; unrated ones are listed separately. score is an ordering aid, not a quality measure.

Parameterstasklimitmax_costprovidermin_context

list_models

List tracked models

All tracked models with full records: Elo and its provenance (elo_source), prices per million tokens, context window, strengths, description. rated is false when the stored Elo is a predecessor's, missing or stale.

Parametersprovider

get_model

Get one model

One tracked model's full record by id (claude, fable, muse, gemini, qwen, grok) or exact name.

Parametersidrequired

list_categories

List use-case categories

The curated use-case categories with their curator-chosen leader and a one-paragraph insight. The leader is a hand-set label, not derived from Elo.

Takes no parameters.

list_articles

List recent articles

Recent Hello, AI articles, newest first: title, date, category, excerpt and URL.

Parameterslimit

get_status

Data freshness and version

Data freshness, app version, model and article counts, the scoring version and snapshot fingerprint, and the rate limit.

Takes no parameters.

Version history

1
  1. v1.0.0LatestOct 29, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.