@aiiq/mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AIIQ_API_BASE | No | Override the API base URL | https://www.aiiq.org |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsA | All public AI models with IQ, the 7 dimension scores, emotional reasoning, rank, and cost. |
| get_modelA | Full detail for one model by id/name, including per-benchmark results and dimension coverage. |
| list_rankingsA | Available leaderboards: composite IQ, effective cost, per-dimension, and per-benchmark. Returns ids + names only. |
| get_rankingA | The ordered models for one ranking id (from list_rankings). |
| list_benchmarksA | Benchmark catalog with descriptions, dimensions, directions, and units. |
| get_methodologyB | How AI IQ is computed (methodology version + summary). |
| compare_modelsA | Side-by-side detail for several models by id/name. Unknown ids are reported, not fatal. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose: listing models, benchmarks, rankings; getting details for single or multiple models; retrieving ranking order; and explaining methodology. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern with imperative verbs (compare, get, list) and underscore separation, creating a predictable and readable set.
Seven tools is well-scoped for a model intelligence ranking service, covering listing, detailed retrieval, comparison, and methodology without being sparse or excessive.
The tool surface covers all essential operations: listing all models, benchmarks, and rankings; retrieving individual model details; comparing models; and understanding the methodology. No obvious gaps for a read-only reference service.