Review-Code
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| XBY_APIKEY | Yes | 你的实际apikey (Your actual API key) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review_codeC | 构建用于代码整体审查与打分的 LLM 提示词（不直接调用 LLM） |
| review_diffC | 构建用于 Git diff 变更审查与打分的 LLM 提示词（不直接调用 LLM） |
| review_fileC | 构建用于单文件审查与打分的 LLM 提示词（不直接调用 LLM） |
| parse_review_scoreC | 从审查文本中解析评分（提取 '总分:XX分' 格式） |
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 4 tools
The tools have distinct purposes: parse_review_score extracts scores from text, while the other three build prompts for different code review contexts (overall code, Git diff, single file). However, review_code, review_diff, and review_file could be confused as they all build LLM prompts for review, differing only in input scope. Descriptions clarify this, but the overlap in function is notable.
All tool names follow a consistent verb_noun pattern with snake_case: parse_review_score, review_code, review_diff, review_file. The naming is predictable and readable, with no deviations in style or convention across the set.
With 4 tools, the count is well-scoped for a code review server. Each tool serves a clear purpose: one for parsing scores and three for building review prompts across different contexts. This is neither too thin nor too heavy for the domain.
The server covers parsing scores and building prompts for various review types, but there are notable gaps. It lacks tools for executing reviews (e.g., calling an LLM), managing review workflows, or handling feedback beyond scores. This limits agents to only prompt construction and score extraction, missing core review operations.