antigravity-review-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_MODEL | No | Override the review model (optional, default: GLM-4.7) | |
| AI_API_KEY | Yes | Your API key (required) | |
| ZHIPU_MODEL | No | Override the review model (optional, default: GLM-4.7) | |
| ZHIPU_API_KEY | No | Backward-compatible fallback key name (optional) | |
| ZHIPU_BASE_URL | No | Override API endpoint (optional) | |
| MAX_REVIEW_ITERATIONS | No | Max tool-calling iterations (optional, default: 20, capped at 50) | |
| REVIEW_MCP_INCLUDE_TRACE | No | Append diagnostic trace details to review responses (optional, true/false) |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review_with_contextA | Review code changes against project context using GLM. Args: diff_target: 'staged', 'unstaged', or a git ref like 'HEAD~1' context_files: Additional files or OpenSpec change folders to read focus_files: Specific files to focus the review on task_description: Optional task description for reviewer intent working_directory: Git repository root to review. Required unless the server was started with --workspace-dir include_trace: Include a compact diagnostic trace in the returned review Returns: The generated code review. |
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
Only one tool exists, so there is no possibility of ambiguity or confusion with other tools.
With a single tool, naming is trivially consistent. The snake_case format is clear and descriptive.
A single tool for a code review server is borderline. While it can perform reviews, the workflow may benefit from additional tools for history or management.
The server lacks tools for retrieving past reviews, listing reviews, or managing review artifacts, leaving significant gaps in a complete review lifecycle.