Hello, AI
Server Details
Ask your assistant which frontier model to use and get a live, Elo-backed answer.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool maps to a distinct resource and action: single model lookup vs. full model listing vs. ranked recommendation, plus separate status, article list, and category list tools. The get_model vs. list_models distinction is the standard singular/plural split and descriptions make the boundary clear. No two tools appear to do the same thing.
All names are snake_case and follow a predictable verb_noun pattern (get_model, get_status, list_articles, list_categories, list_models, recommend_models). The single non-get/list verb (recommend) is still a clear verb-first construction, so the convention holds throughout.
Six tools is well-scoped for a read-only API surface covering models, articles, categories, server status, and recommendations. Every tool corresponds to a real endpoint (GET /api/recommend is referenced explicitly), with no padding or redundancy.
Coverage is strong for listing and recommendation, but there is no way to fetch a single article by id/slug or filter/search articles by category, and list_articles appears limited to recent items with no pagination. An agent can browse and recommend but cannot drill into individual articles or search content, a notable gap for a news/data API.
Available Tools
6 toolsget_modelGet one modelARead-onlyIdempotentInspect
One tracked model's full record by id (gemini, claude, fable, muse, qwen, grok) or exact name.
Inputs: id (required).
get_statusData freshness and versionARead-onlyIdempotentInspect
Data freshness, app version, model and article counts, the scoring version and snapshot fingerprint, and the rate limit.
Inputs: no named parameters.
list_articlesList recent articlesARead-onlyIdempotentInspect
Recent Hello, AI articles, newest first: title, date, category, excerpt and URL.
Inputs: limit.
list_categoriesList use-case categoriesARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
list_modelsList tracked modelsARead-onlyIdempotentInspect
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.
Inputs: provider.
recommend_modelsRecommend models for a taskARead-onlyIdempotentInspect
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.
Inputs: task, limit, max_cost, provider, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Find the right AI model for your job. Free discovery and ranking; tests on your own key.
CroweLM tiers and frontier engines by name, metered per Crowe Logic plan. Ask, list models, account.
Which AI model to call on the providers you have: model id, price and reason.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
Related MCP Servers
- AlicenseAqualityFmaintenanceProvides AI assistants with real-time access to 1000+ AI models including their latest pricing, context windows, capabilities, and specifications. Supports model search, comparison, recommendations, and live testing.31MIT
- AlicenseAqualityDmaintenanceGive your AI assistant real-time LLM/VLM knowledge. Pricing, benchmarks, and recommendations — updated every hour, not every training cycle.4100 npm2MIT
- AlicenseAqualityCmaintenanceEnables users to select the optimal LLM for their specific task by aggregating benchmark data and user intent, returning a ranked shortlist with plain-English rationale.5MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.22 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.