kimi-code-mcp

English | 中文說明

Delegate codebase analysis from Claude to Kimi Code (kimi-for-coding, 256K) — cut Claude-side token cost ~90%.

*Illustrative estimates — savings are on Claude tokens only and depend on the task; Kimi's subscription cost is separate. See Token Economics.

Quick start

# 1. Install Kimi CLI and log in
curl -L code.kimi.com/install.sh | bash
kimi login

# 2. Install via npm
npm install -g kimi-mcp-server

Add to .mcp.json (project-level or ~/.claude/mcp.json for global):

{
  "mcpServers": {
    "kimi-code": {
      "command": "npx",
      "args": ["-y", "kimi-mcp-server"]
    }
  }
}

Run /mcp in Claude Code to verify — you should see kimi-code with 8 tools.

Related MCP server: Ollama MCP Server

How it works

1. Claude calls the kimi_analyze tool when a task needs bulk codebase reading.

2. MCP routes the request to Kimi Code (kimi-for-coding, 256K context) — Kimi reads the entire codebase in one pass.

3. The result is piped back as a structured response — Claude acts on it with precise, targeted edits.

┌──────────────┐  stdio/MCP   ┌──────────────┐  subprocess   ┌──────────────┐
│  Claude Code │ ◄──────────► │ kimi-code-mcp│ ────────────► │ Kimi CLI     │
│  (conductor) │              │ (MCP server) │               │ (256K ctx)   │
└──────────────┘              └──────────────┘               └──────────────┘

Two backends: API vs CLI

The server reaches Kimi two different ways, and each tool uses the one that fits its job. Knowing which is which tells you what you need to set up.

Run kimi_status any time to see which backends are live — it reports the API-configured state and the CLI install/auth state separately.

Guidelines for agents

If you are an AI agent (Claude Code, a subagent, etc.) deciding when to call these tools:

• Cross-check your own work before committing → kimi_verify. Paste the actual diff/code/claim plus the surrounding context (goal, constraints, signatures). Kimi sees only the context string — no repo, no session history. Vague context → useless review.

• Quick model-agnostic programming question → kimi_query. No codebase needed. Returns a different model's opinion.

• Need to understand a large/unfamiliar codebase → kimi_analyze with work_dir. Prefer this over reading 50 files yourself; it's ~10× cheaper in Claude tokens. Requires the CLI to be installed and logged in.

• Drill deeper after an analyze → kimi_resume with the returned session_id (retains up to 256K tokens of prior context).

• Don't know why a Kimi call failed → kimi_status first. "Not authenticated" on the CLI does not affect kimi_query/kimi_verify (those use the API).

• Keep outputs lean. Default detail_level: summary for orientation; raise to normal/detailed only when you need code snippets. Bigger output = more Claude tokens, defeating the purpose.

• Skip Kimi for small/single-file work — Claude reading directly is faster under ~10 files.

MCP server that connects Kimi Code (model kimi-for-coding, 256K context, auto-upgraded) with Claude Code — letting Claude orchestrate while Kimi handles the heavy reading.

What is Kimi Code?

Kimi Code is an AI code agent by Moonshot AI. The model ID kimi-for-coding (1T MoE, 256K context) automatically receives backend upgrades — no version pinning required. It works across Terminal, IDE, and CLI — writing, debugging, refactoring, and analyzing code autonomously.

Key specs:

• 256K token context — reads entire codebases in one pass

• Parallel agent spawning — handles concurrent tasks

• Shell, file, and web access — full developer toolchain

• Install: curl -L code.kimi.com/install.sh | bash

Install from source

If you prefer to build locally instead of using the npm package:

git clone https://github.com/howardpen9/kimi-code-mcp.git
cd kimi-code-mcp && npm install && npm run build

{
  "mcpServers": {
    "kimi-code": {
      "command": "node",
      "args": ["/absolute/path/to/kimi-code-mcp/dist/index.js"]
    }
  }
}

Kimi Code API Setup

There are two ways to configure the Kimi Code API for the CLI:

Option 1: OAuth Login (Recommended)

In the Kimi Code CLI shell, run:

kimi

Then use the /login (or /setup) command:

/login

1. Select Kimi Code as the platform

2. Your browser opens for OAuth authorization

3. Config is saved automatically to ~/.kimi/config.toml

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc

Option 2: Manual API Key Configuration

Get your API Key

1. Visit code.kimi.com

2. Sign in → Settings → API Keys

3. Create a new key (starts with sk-, shown only once)

Edit config file

nano ~/.kimi/config.toml

Add:

[providers.kimi-code]
type = "kimi"
base_url = "https://api.kimi.com/coding/v1"
api_key = "sk-your-api-key"

[models.kimi-for-coding]
provider = "kimi-code"
model = "kimi-for-coding"
max_context_size = 262144
capabilities = ["thinking"]

[defaults]
model = "kimi-for-coding"

Using environment variables (recommended for security)

# Add to ~/.zshrc (macOS) or ~/.bashrc (Linux)
export KIMICODE_API_KEY="sk-your-api-key"

Then reference it in config.toml:

[providers.kimi-code]
type = "kimi"
base_url = "https://api.kimi.com/coding/v1"
api_key = "${KIMICODE_API_KEY}"

Multi-provider config example

You can configure both Kimi Code and Moonshot side by side:

[providers.kimi-code]
type = "kimi"
base_url = "https://api.kimi.com/coding/v1"
api_key = "${KIMICODE_API_KEY}"

[providers.moonshot-cn]
type = "kimi"
base_url = "https://api.moonshot.cn/v1"
api_key = "${MOONSHOT_API_KEY}"

[models.kimi-for-coding]
provider = "kimi-code"
model = "kimi-for-coding"
max_context_size = 262144
capabilities = ["thinking"]

[models.kimi-k2]
provider = "moonshot-cn"
model = "kimi-k2-0905-preview"
max_context_size = 256000
capabilities = ["thinking"]

[defaults]
model = "kimi-for-coding"

Switch models at any time with /model or /model kimi-k2 in the CLI.

Kimi Code vs Moonshot

What You Can Do

Just tell Claude what you need. It will delegate to Kimi automatically:

Why This Exists

Claude Code is powerful but expensive. Every file it reads costs tokens. Meanwhile, many tasks — pre-reviewing large codebases, scanning for patterns, generating audit reports — are high-certainty work that doesn't need Claude's full reasoning power.

How It Saves Tokens

                          ┌─────────────────────────────┐
                          │   You (the developer)       │
                          └──────────┬──────────────────┘
                                     │ prompt
                                     ▼
                          ┌─────────────────────────────┐
                          │   Claude Code (conductor)   │
                          │   - orchestrates workflow    │
                          │   - makes decisions          │
                          │   - writes & edits code      │
                          └──────┬──────────────┬───────┘
                      precise    │              │  delegate
                      edits      │              │  bulk reading
                      (tokens)   │              │  (FREE)
                                 ▼              ▼
                          ┌──────────┐   ┌──────────────┐
                          │ your     │   │  Kimi Code   │
                          │ codebase │   │  - 256K ctx  │
                          └──────────┘   │  - reads all │
                                         │  - reports   │
                                         └──────────────┘

1. Claude receives your task → decides it needs codebase understanding

2. Claude calls kimi_analyze via MCP → Kimi reads the entire codebase (256K context, near-zero cost)

3. Kimi returns a structured analysis

4. Claude acts on the analysis with precise, targeted edits

Result: Claude only spends tokens on decision-making and code writing, not on reading files.

Mutual Code Review with Kimi Code

kimi-for-coding is a 1T MoE model designed for deep code comprehension. This enables AI pair review:

1. Kimi pre-reviews — 256K context means it sees the entire codebase at once: security issues, anti-patterns, dead code, architectural problems

2. Claude cross-examines — reviews Kimi's findings, challenges questionable items, adds its own insights

3. Two perspectives — different models catch different things. What one misses, the other finds

Use Kimi as a Code Reviewer

Beyond ad-hoc analysis, you can use Kimi as a dedicated reviewer in your workflow:

PR Review Workflow

┌──────────────┐   diff    ┌──────────────┐  structured  ┌──────────────┐
│   Your PR    │ ────────► │  Kimi Code   │  findings    │  Claude Code │
│  (changes)   │           │  (reviewer)  │ ────────────►│  (decision)  │
└──────────────┘           └──────────────┘              └──────────────┘

Continuous Audit Pattern

Each review session can be resumed (kimi_resume) — Kimi retains up to 256K tokens of context from previous sessions, building understanding over time.

What Kimi Reviews Well

Tools

Output Control Parameters

kimi_analyze and kimi_resume support these parameters to control output size:

kimi_query also supports max_output_tokens and include_thinking.

Token Economics

                    Without kimi-code-mcp        With kimi-code-mcp (normal)
                    ─────────────────────        ───────────────────────────
Raw source:         50 files × ~4K = 200K        Kimi reads (subscription cost)
Claude reads:       200K tokens                  5-15K token report
Claude token cost:  $$$                          $

Compression ratio by detail_level:

When savings happen:

• Large codebases (50+ files) — architecture understanding, cross-file scanning

• Security audits, dead code detection, API consistency checks

• Pre-review before targeted edits (scan first → edit specific files)

When to skip and let Claude read directly:

• Small codebases (<10 files) — direct reading is faster

• Single-file modifications — Claude's built-in file reading is sufficient

• When you need every line of code — detailed output approaches raw reading cost

Implementation details

Under the hood:

1. Claude Code calls an MCP tool (e.g., kimi_analyze)

2. This server spawns the kimi CLI with the prompt and codebase path

3. Kimi autonomously reads files, analyzes the code (up to 256K tokens)

4. The result is parsed from Kimi's JSON output and returned to Claude Code

5. Claude acts on the structured results — edits, plans, or further analysis

CLI Invocation Reference

The MCP server calls the Kimi CLI in non-interactive (print) mode:

kimi --work-dir <path> --print -p "<prompt>"

Advanced Setup

For development (auto-recompile on changes):

{
  "mcpServers": {
    "kimi-code": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/kimi-code-mcp/src/index.ts"]
    }
  }
}

npm

Published as kimi-mcp-server on npm.

npx kimi-mcp-server          # run directly
npm install -g kimi-mcp-server # install globally

Project Structure

src/
├── index.ts           # MCP server setup, tool definitions, API-vs-CLI routing
├── kimi-api.ts        # Direct Kimi Code API client (kimi_query / kimi_verify)
├── kimi-runner.ts     # Spawns kimi CLI, parses output, handles timeouts
├── cache-manager.ts   # Session cache (warmup, reuse, invalidation)
└── session-reader.ts  # Reads Kimi session metadata from ~/.kimi/

Contributing

See CONTRIBUTING.md for guidelines.

Changelog

See CHANGELOG.md for version history.

License

MIT