加载中…
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
io.github.n24q02m/crg 是 ChatHome Skills 收录的 MCP 条目,来源为 Official MCP Registry,质量分 78/100。 作为 Model Context Protocol 服务器,它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具,让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录,每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势,完整算法说明见来源页。安装命令已列于上方,可直接复制使用。 在将 io.github.n24q02m/crg 加入生产 agent 工作流前,请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
uvx better-code-review-graph==3.30.0运行此命令前,请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-06T02:16:39.776901Z",
"publishedAt": "2026-10-06T02:16:39.776901Z",
"statusChangedAt": "2026-10-06T02:16:39.776901Z"
}
},
"server": {
"name": "io.github.n24q02m/crg",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "3.30.0",
"packages": [
{
"version": "3.30.0",
"transport": {
"type": "stdio"
},
"identifier": "better-code-review-graph",
"runtimeHint": "uvx",
"registryType": "pypi",
"environmentVariables": [
{
"name": "EMBEDDING_MODELS",
"description": "Embedding models in selection order; the current runtime uses the first provider/model entry; empty = local ONNX"
},
{
"name": "LOCAL_EMBEDDING_MODEL",
"description": "Built-in fastretrieval model ID or local directory with fastretrieval-manifest.json"
},
{
"name": "LOCAL_RERANK_MODEL",
"description": "Fastretrieval TextCrossEncoder model ID; empty = reranking disabled"
},
{
"name": "LOCAL_EMBEDDING_DIM",
"description": "Required positive output dimension for an external local embedding ID without a manifest"
},
{
"name": "LOCAL_EMBEDDING_MODEL_FILE",
"description": "ONNX file path inside a manifest-backed local embedding directory"
},
{
"name": "LOCAL_EMBEDDING_POOLING",
"description": "Explicit pooling for an external local embedding ID without a manifest"
},
{
"name": "LOCAL_EMBEDDING_NORMALIZE",
"description": "Explicit L2 normalization for an external local embedding ID without a manifest"
},
{
"name": "HULL_EMBED_API_KEY",
"isSecret": true,
"description": "API key for the [models.embed] cell transport (OpenRouter pre-wired default); host-injected, overrides the cell api_key"
},
{
"name": "HULL_CHAT_API_KEY",
"isSecret": true,
"description": "API key for the [models.chat] cell transport (OpenRouter pre-wired default); host-injected, enables LLM summaries when the cell model is set"
},
{
"name": "EMBEDDING_BACKEND",
"description": "DEPRECATED (honored one release): embedding backend override 'local' or 'cloud'. Use EMBEDDING_MODELS instead."
}
]
}
],
"repository": {
"url": "https://github.com/n24q02m/crg.git",
"source": "github"
},
"description": "Token-efficient code review knowledge graph: semantic search and call-graph resolution."
}
}