Compare MCP
未认领Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.
agentagenticchatclaude-codeclipcursorgeminigptkimillm-inference
安装
$
claude mcp add -s user compare-mcp -- python -m compare_mcp更多Communication服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
7 个工具中显示 7 个
文档中列出的工具 (7)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
compare_debate
Models critique each other, then synthesize
compare_diff
Extract unique vs shared insights with fuzzy dedup
compare_models
List configured providers (no API keys exposed)
compare_run
Fan out code review to providers in parallel
compare_status
Read todos grouped by status
compare_todo_update
Update a todo's status
compare_todos
Write ranked findings to SQLite