Kimi MCP Server

io.github.x51xxxPublished by GitHub account x51xxxv0.2.0Updated Oct 24, 2026

MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

A local stdio MCP server that lets an assistant call Moonshot AI's Kimi Code CLI as a sub-agent for code analysis, review, brainstorming and batch tasks.

What you can do
Ask Kimi to analyze files referenced by path, with model, thinking mode, output format and session resume options, and pass through other MCP servers to it via a config file and extra directories for multi-root projects. Run structured brainstorming sessions using divergent, convergent, SCAMPER, design-thinking or lateral modes. Execute sequential or parallel atomic tasks with priority and stop-on-error, returning a structured report. Review code changes in the working tree, a branch diff or a specific commit by collecting git diff output. List, delete or clear conversation sessions, and diagnose CLI installation, authentication and session state.
When to use it
Useful when you work in an MCP-aware editor or Claude Desktop and want a second coding agent (Kimi) available without leaving that interface, for code review, file analysis or ideation. It suits users who already have or are willing to install the Kimi Code CLI.
Requirements
Runs locally over stdio as the npm package @trishchuk/kimi-mcp-server, so Node.js is needed, plus the Kimi Code CLI installed separately. Authentication is either an interactive Kimi login or the MOONSHOT_API_KEY environment variable. Optional variables KIMI_MCP_CWD, KIMI_SESSION_TTL_MS and KIMI_MAX_SESSIONS control working directory and session limits. Desktop clients only.
Before you install
The server spawns the Kimi CLI, which sends your prompts and referenced file contents to Moonshot AI's service, so avoid pointing it at sensitive code. MOONSHOT_API_KEY is a secret forwarded to the CLI. Print mode auto-approves actions, and the yolo and afk options are approval shortcuts, so Kimi may act without per-step confirmation. review-changes reads git diffs, and session tools can delete or clear sessions.

Installation

In SourceWeft

  1. Open Kimi MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Kimi MCP Server

[License: MIT]

MCP server (stdio) that bridges Claude / Cursor / any MCP client to Moonshot AI's Kimi Code CLI.

Architecture mirrors @trishchuk/codex-mcp-tool — same patterns, adapted to Kimi's flag surface (--print, --quiet, -r, --continue, --add-dir, --mcp-config-file, --config).

Why

Kimi K2.6 (April 2026) is a 1T-parameter MoE open-weight model with native agent-swarm orchestration, 262k context, and SWE-Bench Pro on par with GPT-5.5. Kimi Code CLI is the reference agent harness. This server lets MCP-aware editors call Kimi as a sub-agent without leaving their primary interface.

Install

sh
npm install -g @trishchuk/kimi-mcp-server

You also need Kimi Code CLI:

sh
curl -LsSf https://code.kimi.com/install.sh | bash# ORuv tool install --python 3.13 kimi-cli

Then run kimi once and use /login to authenticate via the Kimi Code platform — or set MOONSHOT_API_KEY.

Configure (Claude Desktop / Cursor / Claude Code)

Minimal — working directory is auto-detected from PWD / INIT_CWD / process.cwd(), just like codex-mcp-tool:

json
{  "mcpServers": {    "kimi": {      "command": "kimi-mcp"    }  }}

Pin a specific project root only if your client launches the server from somewhere unrelated:

json
{  "mcpServers": {    "kimi": {      "command": "kimi-mcp",      "env": { "KIMI_MCP_CWD": "/absolute/path/to/your/project" }    }  }}

You can also override per call via the workingDir argument on ask-kimi, or let the server infer it from @path/to/file references in the prompt — same priority chain as codex-mcp-tool: workingDir arg → KIMI_MCP_CWD → PWD → INIT_CWD → @path inference → process.cwd().

Tools

ToolWhat it does
ask-kimiMain entry — file analysis (@path), session resume, MCP passthrough
brainstormStructured ideation (divergent / convergent / SCAMPER / design-thinking / lateral / auto)
batch-kimiSequential or parallel atomic tasks with priority, stop-on-error, structured report
review-changesCode review of working tree / branch diff / specific commit (collects git diff and prompts Kimi)
list-sessionsList, delete, or clear active conversation sessions
healthDiagnose Kimi CLI installation, auth, and session state
ping / Help / versionSmoke tests + help passthrough

ask-kimi highlights

  • prompt — supports @path/to/file to drop file context (Kimi reads via working dir).
  • model — overrides default_model at runtime via --config. Known: kimi-for-coding, kimi-k2-6, kimi-k2-thinking-turbo, kimi-k2-5, kimi-latest.
  • thinking — toggles thinking mode (writes default_thinking into runtime config).
  • outputFormat — text (default) or stream-json (JSONL of assistant + tool messages, parsed transparently).
  • responseMode — clean (default; final assistant text only) or full (tool calls + stderr log + final).
  • sessionId — workspace-isolated session ID (md5 of repo:head:path). The server tracks the native Kimi session ID returned by the CLI and replays it via kimi -r <id>.
  • continueLatest — sets --continue (resume the most recent session in the cwd).
  • mcpConfigFile — passes --mcp-config-file so Kimi can talk to other MCP servers from inside this process.
  • addDirs — repeats --add-dir for multi-root projects.
  • yolo / afk — approval shortcuts (print mode auto-approves anyway, but useful for documentation/logging).

CLI compatibility

FeatureKimi CLI
Print / non-interactive--print (required for MCP); --quiet = --print --output-format text --final-message-only
JSON streaming--output-format=stream-json, --input-format=stream-json
Sessions--continue, --session <id>, -r <id>
Configuration--config-file <path>, --config '<json/toml>'
Workspacespawn cwd + --add-dir <path> (no --cd flag)
MCP passthrough--mcp-config-file or kimi mcp add
Exit codes0 ok, 1 fatal, 75 retryable transient

Environment

VarDefaultPurpose
KIMI_MCP_CWD—Override working directory for every tool call
KIMI_SESSION_TTL_MS86400000 (24h)Session expiration
KIMI_MAX_SESSIONS50Max concurrent sessions
MOONSHOT_API_KEY—Forwarded to Kimi CLI for unattended auth

Development

sh
npm installnpm run build       # tsc → dist/npm run lint        # tsc --noEmitnode dist/index.js  # smoke run on stdio

License

MIT — Taras Trishchuk

Source: README.md at commit 83eee42

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts