Kimi MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIMI_MCP_CWD | No | Override working directory for every tool call | |
| MOONSHOT_API_KEY | No | Forwarded to Kimi CLI for unattended auth | |
| KIMI_MAX_SESSIONS | No | Max concurrent sessions | 50 |
| KIMI_SESSION_TTL_MS | No | Session expiration in milliseconds | 86400000 |
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 | {} |
| logging | {} |
| prompts | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask-kimiB | Execute Kimi Code CLI with file analysis (@syntax), session resume, MCP passthrough, and safety controls. |
| batch-kimiA | Delegate multiple atomic tasks to Kimi for batch processing. Ideal for repetitive operations, mass refactoring, and automated transformations. |
| review-changesA | Run a code review against the current repository using Kimi (collects git diff + structured review prompt). |
| brainstormA | Generate creative ideas using structured frameworks with domain context and feasibility analysis. |
| bg-kimiA | Run Kimi CLI as a detached background task. Subactions: start (returns taskId), status, tail (log output), stop, remove, list. Use for long-running autonomous work — the MCP call returns immediately and you poll status later. |
| plan-kimiA | Generate a structured implementation plan using Kimi's --plan mode. Use BEFORE coding to get steps, files-to-touch, risks, and open questions. Distinct from ask-kimi: uses --plan flag (different system prompt) and parses structured output. |
| digest-kimiA | Ingest many files at once and answer a focused question. Uses Kimi's 262K context to swallow whole modules / docs that don't fit in the caller's context. Walks directories, filters by extension, truncates oversized files, caps total payload. Returns a concentrated brief. |
| delegate-kimiA | Delegate an implementation task to Kimi in an isolated git worktree. Kimi runs autonomously (--yolo) on a fresh branch, optionally looping against a test command. Returns a taskId; later 'collect' to grab the diff. Safe: changes are sandboxed, caller reviews & applies. |
| list-sessionsB | List active conversation sessions with metadata, or manage them (delete/clear) |
| healthA | Check Kimi CLI installation, authentication, and session health |
| pingC | Echo |
| HelpA | Show Kimi CLI help output |
| versionA | Display version and system information |
| metricsA | Expose Prometheus-formatted metrics for Kimi MCP server |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask-kimi | Execute Kimi Code CLI in print mode with optional session continuity |
| batch-kimi | Execute multiple atomic Kimi tasks in batch mode for efficient automation |
| review-changes | Review uncommitted changes / branch diff / specific commit with Kimi |
| brainstorm | Create structured brainstorming with chosen methodology and analysis |
| list-sessions | View and manage active Kimi sessions |
| health | Diagnose Kimi CLI installation, authentication, and session health |
| ping | Echo test message with structured response. |
| Help | Receive help information |
| version | Get version information for Kimi CLI and MCP server |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool has a clearly distinct purpose: from single queries (ask-kimi) to batch processing, code review, brainstorming, background tasks, planning, file ingestion, sandboxed delegation, session management, and server info. No two tools overlap in functionality.
Most tools use lowercase with hyphens (e.g., ask-kimi, batch-kimi), but there are inconsistencies: some are single words (ping, health, version), 'Help' is capitalized, and patterns vary between verb-noun and noun-verb. The naming is readable but not fully consistent.
With 14 tools, the server provides a comprehensive interface to the Kimi CLI, covering core interactions (query, batch, planning, code review, brainstorming), background tasks, file digestion, sandboxed delegation, and management. The count feels well-scoped for its purpose.
The tool surface covers the major workflows expected from a CLI-based coding assistant: interactive queries, batch processing, code review, planning, brainstorming, file ingestion, and sandboxed execution. Minor gaps might include a direct file-editing tool, but the existing tools enable comprehensive automation.