Kimi Code Mcp

kimi-code-mcp

English | [中文說明](README_zh.md)

---

Illustrative estimates. The ~90% is Claude-side token reduction on analysis-heavy tasks — not total cost: Kimi's own subscription still applies. The monorepo row mirrors the example below; the PDF/commits rows are rough sketches.

---

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

| Task | Claude only | Claude + kimi-code-mcp | Claude-side savings | |------------------------------|-------------|------------------------|---------------------| | Analyze 200-file monorepo | ~250K tok | ~25K tok | ~90% | | Summarize 50-page RFC PDF | ~60K tok | ~6K tok | ~90% (sketch) | | Cross-reference 100 commits | ~80K tok | ~8K tok | ~90% (sketch) |

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

> [!TIP] > You don't need the CLI for the common case. kimi_query and kimi_verify call the Kimi Code API directly — no Python CLI install or kimi login required. Just provide an API key via $KIMICODE_API_KEY or ~/.kimi/config.toml (see [Kimi Code API Setup](#kimi-code-api-setup)). Only the codebase-reading tools (kimi_analyze, kimi_resume) need the CLI. See [Two backends: API vs CLI](#two-backends-api-vs-cli) for the full split.

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.

| Backend | How it talks to Kimi | What it needs | Sees your codebase? | |---------|----------------------|---------------|---------------------| | Direct API | HTTPS to api.kimi.com/coding/v1 | An API key only ($KIMICODE_API_KEY or ~/.kimi/config.toml) | ❌ No — you paste in the context | | Local CLI | Spawns the kimi binary as a subprocess | CLI installed and kimi login done | ✅ Yes — reads files from disk |

| Tool | Backend | Why | |------|---------|-----| | kimi_query | API (CLI only if no key configured) | Contextless Q&A — no codebase needed, so the API is simpler and has no login dependency | | kimi_verify | API | You pass the code/diff/claim inline; Kimi judges it as an independent third party | | kimi_analyze | CLI | Must read your whole codebase (256K ctx) from disk | | kimi_resume | CLI | Continues a stateful CLI session that holds prior codebase context | | kimi_list_sessions, kimi_cache_*, kimi_status | local | Read local session/cache metadata |

> [!IMPORTANT] > Most users only need the API key. If you just want a second opinion / verification (kimi_query, kimi_verify), set the API key and you're done — skip the CLI entirely. Install + kimi login only when you want Kimi to read your codebase via kimi_analyze / kimi_resume.

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.

Kimi Code sits on the efficiency frontier — near-Claude intelligence at 10x lower cost. kimi.com/code

> [!TIP] > Stop paying Claude to read files. Kimi Code delivers frontier-class code intelligence at a fraction of the cost (see chart above). Delegate bulk codebase scanning to Kimi (256K context, near-zero cost) and let Claude focus on what it does best — reasoning, decisions, and precise code edits. One kimi_analyze call can replace 50+ file reads.

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

> [!WARNING] > Kimi Code membership required. All tools ultimately hit Kimi Code, which needs an active Kimi Code plan. The API tools (kimi_query, kimi_verify) authenticate with an API key; the codebase tools (kimi_analyze, kimi_resume) additionally need the CLI installed + kimi login. See kimi.com/code for pricing tiers and quotas.

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

> [!NOTE] > Kimi Code API and Moonshot API are separate providers — their API keys are not interchangeable.

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

> [!NOTE] > zsh: command not found: kimi after install? The installer puts the binary at ~/.local/bin/kimi, which may not be on your PATH. Add it (then restart your shell or open a new tab): > ``bash > echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc > ` > The MCP server calls the binary by absolute path, so this only affects running kimi yourself in a terminal (e.g. for kimi login`).

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

| Feature | Kimi Code | Moonshot | |---------|-----------|----------| | Focus | Optimized for coding | General-purpose chat | | Endpoint | api.kimi.com/coding/v1 | api.moonshot.cn/v1 | | API Key | Separate — apply at code.kimi.com | Separate | | SearchWeb / FetchURL | Built-in | Not available | | Context | 262K | 256K |

What You Can Do

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

| Prompt | What happens | |--------|-------------| | "Analyze this codebase's architecture" | Kimi reads all files (256K ctx), Claude acts on the report | | "Scan for security vulnerabilities, then review Kimi's findings" | Kimi audits, Claude cross-examines — AI pair review | | "Map all dependencies of the auth module, then plan the refactoring" | Kimi builds the dependency graph, Claude plans the changes | | "Review the recent changes for regressions and edge cases" | Kimi reviews full context (not just the diff), Claude synthesizes | | "Resume the last Kimi session and ask about the API design" | Kimi retains 256K tokens of context across sessions |

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.

> [!IMPORTANT] > The cost equation: Claude reads 50 files to understand your architecture = expensive. Kimi reads 50 files via kimi_analyze = near-zero cost. Claude then acts on Kimi's structured report = minimal tokens. Total savings: 60-80% fewer Claude tokens on analysis-heavy tasks.

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

| When | What | Why | |------|------|-----| | Before merging | Kimi scans diff + affected modules | Catch regressions early | | Weekly | Full codebase sweep | Accumulated tech debt | | Pre-release | Security-focused audit | Ship with confidence |

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

| Review Type | Why Kimi Excels | |-------------|----------------| | Security audit | 256K context sees full attack surface, not just isolated files | | Dead code detection | Can trace imports/exports across entire codebase | | API consistency | Compares patterns across all endpoints simultaneously | | Dependency analysis | Maps full dependency graph in one pass | | Architecture review | Sees the forest and the trees at the same time |

Tools

| Tool | Description | Timeout | |------|-------------|---------| | kimi_analyze | CLI — deep codebase analysis (architecture, audit, refactoring) | 10 min | | kimi_query | API — quick programming questions, no codebase context (CLI only if no key configured) | 2 min | | kimi_verify | API — independent third-party verification of code/diffs/claims; no CLI required, context-driven | 5 min | | kimi_list_sessions | List existing Kimi sessions with metadata | instant | | kimi_resume | CLI — resume a previous session (up to 256K token context) | 10 min | | kimi_status | Report API-configured

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: howardpen9
• Source: howardpen9/kimi-code-mcp
• License: MIT
• Homepage: https://github.com/howardpen9/kimi-code-mcp#readme

Install and usage instructions live in the source repository linked above.