kimi-code-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kimi_analyzeA | Send a prompt to Kimi Code for codebase analysis. Kimi reads the codebase (256K context) and returns a compressed, structured report. CACHE BEHAVIOR: If session_id is not provided, the MCP server will automatically use cached sessions when available.
Output is budget-controlled: Kimi reads 200K+ tokens of source but returns a 5-15K token analysis (configurable via detail_level). Use kimi_resume to drill deeper into specific areas. Takes 1-5 minutes for large codebases. |
| kimi_queryA | Ask Kimi Code a question without codebase context. Use for general programming questions, algorithm explanations, or getting a second opinion from Kimi's model. |
| kimi_list_sessionsA | List existing Kimi Code sessions with titles, working directories, and timestamps. Use to find session IDs for kimi_resume. |
| kimi_cache_statusB | View session cache statistics and status. Shows cache hits/misses, active sessions, and performance metrics. Use this to monitor cache effectiveness and troubleshoot issues. |
| kimi_cache_invalidateA | Manually invalidate session cache entries. Use when you want to force fresh analysis or if you suspect cached sessions are stale. |
| kimi_resumeA | Resume an existing Kimi Code session with a new prompt. The session retains all previous context (up to 256K tokens). Use kimi_list_sessions to find session IDs first. Ideal for drilling deeper after an initial kimi_analyze scan. |
| kimi_statusA | Check Kimi CLI installation status, version, and authentication. Use this to diagnose issues before running analysis. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: analyzing codebase, managing cache, listing sessions, resuming sessions, general queries, and checking status. No overlapping functionality.
All tools follow a consistent 'kimi_' prefix with snake_case verbs describing the action (analyze, cache_invalidate, cache_status, list_sessions, query, resume, status).
7 tools cover the full lifecycle of Kimi Code interaction: setup, analysis, cache management, session management, and general queries—without excess.
The tool set provides complete coverage for codebase analysis with Kimi Code, including status checks, analysis, session resumption, cache management, and general queries. No obvious gaps.