gpt-cross-validator
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gemini_critiqueA | Gemini Pro를 사용하여 계획/설계를 검토합니다. Claude와 독립적인 교차검증용. |
| gemini_reviewB | Gemini Pro를 사용하여 코드 품질을 검토합니다. Claude와 독립적인 교차검증용. |
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 2 tools
The two tools have clearly distinct scopes: one critiques plans/designs while the other reviews code quality. Despite both using Gemini, the target artifact is unambiguously different, so an agent can easily select the appropriate tool.
Both tools follow the consistent `<provider>_<verb>` pattern (gemini_critique, gemini_review), using lowercase and underscores. The naming style is uniform and predictable.
With only two tools, the server is minimal but each tool serves a specific validation type. While it doesn't reach the typical 3-15 range, the narrow scope of cross-validation makes the count borderline acceptable.
The server covers the two main artifact types (plans/designs and code) that would need independent validation. No additional validation types are implied by the server's purpose, so the surface is fully sufficient.