ai-compass
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | Yes | Your Anthropic API key used for the recommendation engine (Claude). |
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 |
|---|---|
| recommend_modelsD | – |
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 1 tool
With only one tool available, there is no possibility of confusing it with another tool. However, the complete absence of a description leaves the exact scope and intended use of 'recommend_models' undefined.
The single tool follows a clear verb_noun pattern (recommend_models), which aligns with recommended conventions. Consistency across a set cannot be fully verified with only one sample, but the chosen pattern is sound.
A single tool is insufficient for the implied scope of an 'ai-compass' server, which would typically require capabilities like listing available models, retrieving specifications, or comparing options. The guidelines specifically flag a single tool as 'too few' for most scopes.
The surface covers only the recommendation action with no supporting tools for model discovery, detail retrieval, or filtering. The lack of a description further exacerbates the gap, leaving agents uncertain about required parameters and return formats.