{"id":"howardpen9-kimi-code-mcp","name":"kimi-code-mcp","af_score":56.2,"security_score":64.2,"reliability_score":28.8,"what_it_does":"Provides an MCP server that lets Claude Code delegate bulk codebase analysis to Kimi Code (Kimi K2.5, up to 256K context) by spawning the Kimi CLI and returning parsed JSON results via MCP tools such as kimi_analyze and kimi_resume.","best_when":"You have large, multi-file repositories and want Claude to reason/edit using compressed, cross-file analysis output rather than reading everything itself.","avoid_when":"When you need every line verbatim from the analysis (detailed output approaches raw reading costs) or when external execution/subprocesses are disallowed.","last_evaluated":"2026-03-30T15:27:52.496174+00:00","has_mcp":true,"has_api":false,"auth_methods":["Kimi Code CLI OAuth login (/login or /setup) with config stored in ~/.kimi/config.toml","Manual API key configuration for Kimi Code (api.kimi.com/coding/v1) via ~/.kimi/config.toml or environment variable KIMICODE_API_KEY"],"has_free_tier":true,"known_gotchas":["Requires valid Kimi Code membership and a completed `kimi login` (or equivalent API key configuration) because the MCP server invokes the Kimi CLI.","The MCP tool name is `kimi_analyze`, but the underlying CLI uses flags like `--work-dir`, `--print`, `-p/--prompt` (no `kimi analyze` subcommand).","Non-interactive execution depends on subprocess behavior; failures may be surfaced via MCP without clear documented mapping."],"error_quality":0.0}