Compare MCP
UnclaimedCompare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.
Install
claude mcp add -s user compare-mcp -- python -m compare_mcpSet up this server
More in Communication
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
7 of 7 tools
Documented tools (7)
From project documentation. A server handshake does not verify each tool’s description or behavior.
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
Tool change history
FAQ
Questions about Compare MCP Server
- How do I connect Compare MCP Server to Claude?
- The listing records `claude mcp add -s user compare-mcp -- python -m compare_mcp` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code as compatible clients.
- Is Compare MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Compare MCP Server do?
- Compare MCP Server documents 7 tools to the agent, including compare_debate, compare_diff, compare_models. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.