A
licenseA
qualityB
maintenanceDelegates coding tasks to your locally installed pi CLI, inheriting providers, models, and extensions, with persistent sessions and cancellable calls.
6
59 npm
MIT
kimi-cli-mcp
by minmax
Related Servers
Alternatives to kimi-cli-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceBridges MCP clients to Moonshot AI's Kimi Code CLI, enabling file analysis, brainstorming, batch tasks, code reviews, and session management within editors like Claude Desktop and Cursor.14433 npm1MIT
- AlicenseAqualityCmaintenanceEnables Codex to delegate coding tasks to an OpenCode CLI locally, returning structured results such as exit codes, session summaries, tool calls, and git diffs.2MIT
- AlicenseNot gradedqualityBmaintenanceBridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.5 npm6MIT
- AlicenseBqualityDmaintenanceMCP server wrapping Kimi Code CLI (kimi-k2.5) to provide tools for filesystem, shell, web, and agent operations.1414 npm7MIT
- FlicenseAqualityBmaintenanceProvides Claude Code with an asynchronous expert advisory service via kimi CLI, maintaining conversation-level memory and automatically binding to kimi sessions for cost-effective guidance at key checkpoints.5-
TDQS
A4.5/5.0
Scored across 7 tools
Disambiguation5/5
Each tool targets a distinct phase of the Kimi session lifecycle: start (kimi), resume (kimi_reply), message a running turn (kimi_send), list running (kimi_running), list all (kimi_sessions), read history (kimi_history), and list models (kimi_models). The overlapping pairs (reply/send, running/sessions) are explicitly differentiated by execution state.
Naming Consistency5/5
All tools share the kimi_ prefix with lowercase snake_case names. The only deviation is the root verb `kimi` itself for starting a new session, which is a natural base command; the pattern is otherwise uniform (kimi_ + verb/noun).
Tool Count5/5
Seven tools cover the full lifecycle of orchestrating a Kimi CLI agent: start, resume, send, list running/all, history, and models. This is well-scoped for the server's stated purpose without redundancy.
Completeness4/5
Core session lifecycle is well covered: start, reply, send while running, list running/all, read history, and list models. Missing an explicit cancel/stop operation for running turns, which is a minor gap but likely handled outside the tool surface.
Maintenance
ActivityMaintained
ResponsivenessNo issues