Package Exports

n8n-nodes-claude-code-cli
n8n-nodes-claude-code-cli/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (n8n-nodes-claude-code-cli) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

   _____ _                 _         _____          _
  / ____| |               | |       / ____|        | |
 | |    | | __ _ _   _  __| | ___  | |     ___   __| | ___
 | |    | |/ _` | | | |/ _` |/ _ \ | |    / _ \ / _` |/ _ \
 | |____| | (_| | |_| | (_| |  __/ | |___| (_) | (_| |  __/
  \_____|_|\__,_|\__,_|\__,_|\___|  \_____\___/ \__,_|\___|

           ⚡ for n8n ⚡

n8n-nodes-claude-code-cli

🤖 Bring the power of Claude Code AI directly into your n8n workflows

Automate code reviews • Generate documentation • Fix bugs • Build coding bots

Getting Started • Use Cases • Documentation

✨ Features

🐳 Multiple Connection Modes

Execute Claude Code locally, via SSH, or inside Docker containers

🔄 Session Management

Maintain multi-turn conversations across workflow executions

🎯 Tool Permissions

Fine-grained control over which tools Claude Code can use

📁 Context File Support

Include files and directories as context for code analysis

🧠 Multiple Models

Support for Opus, Sonnet, Haiku and specific versions

📊 Rich Output

Detailed metadata including costs, tokens, and session IDs

⚡ Quick Start

1️⃣ Install  →  2️⃣ Setup Claude Code  →  3️⃣ Authenticate  →  4️⃣ Create Workflow  →  5️⃣ Run!

📋 Step-by-step guide

1️⃣ Install the node

Install the node in n8n community nodes

Search for "n8n-nodes-claude-code-cli" in the n8n community nodes interface. Then install the node.

Install the node locally with git:

I recommend using git to install the node locally. If there is a supply chain attack, you will not be affected by the automatic updates of the community nodes of n8n. And therefore your service will not be corrupted. Supply chain attacks are very dangerous, more and more frequent and can compromise your service. It is therefore recommended to use git to install the node locally.

git clone https://github.com/n8n-io/n8n-nodes-claude-code-cli.git
cd n8n-nodes-claude-code-cli
npm install
npm run build

Install locally with npm:

npm install n8n-nodes-claude-code-cli

For local installation you need to add the environment variable - N8N_CUSTOM_EXTENSIONS=/home/node/.n8n/custom in your n8n configuration file.

2️⃣ Set up Claude Code

Choose your deployment method (see Installation)

3️⃣ Authenticate with Claude

# For Docker
docker exec -it your-container-name claude login

# For SSH or Local
claude login

4️⃣ Create credentials in n8n

Go to Settings → Credentials → Add Credential and select your connection type

5️⃣ Add the node and run!

Search for "Claude Code" in the node panel, configure, and execute

🐳 Docker (Recommended)

Why Docker? Isolation, easy setup, portability, and security.

Option 1: Node.js Container (Lightweight)

Best for code analysis without system tools:

FROM node:24-slim

# Install Claude Code CLI
RUN npm install -g @anthropic-ai/claude-code

# Set up workspace
WORKDIR /workspace

# Keep container running
CMD ["tail", "-f", "/dev/null"]

# docker-compose.yml
services:
  claude-code-runner:
    build: .
    volumes:
      - ./workspace:/workspace

Option 2: Debian Container (Full Tooling)

Best when Claude Code needs system tools (git, build tools, etc.):

FROM debian:bookworm-slim

# Install Node.js and common tools
RUN apt-get update && apt-get install -y \
    curl git build-essential \
    && curl -fsSL https://deb.nodesource.com/setup_24.x | bash - \
    && apt-get install -y nodejs \
    && rm -rf /var/lib/apt/lists/*

# Install Claude Code CLI
RUN npm install -g @anthropic-ai/claude-code

WORKDIR /workspace
CMD ["tail", "-f", "/dev/null"]

🔑 Authenticate:

docker exec -it claude-code-runner claude login

⚙️ n8n Credentials:

Parameter	Value
Container Name	`claude-code-runner`
Working Directory	`/workspace`

🔐 SSH (Alternative)

Why SSH? Full system access and dedicated resource isolation.

Setup Instructions

Set up a VM (AWS EC2, GCP, DigitalOcean, etc.)

Install Claude Code:

# Install Node.js
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt-get install -y nodejs

# Install Claude Code
npm install -g @anthropic-ai/claude-code

# Authenticate
claude login

Configure SSH with key-based authentication

⚙️ n8n Credentials:

Parameter	Value
Host	Your VM IP/hostname
Port	`22`
Auth Method	`privateKey`

💻 Local (Not Recommended)

⚠️ Security concerns - Claude Code runs in the same context as n8n

Why not recommended?

Security risks (shared execution context)
Resource contention
Harder to manage and update

If you must use local:

Install Claude Code inside your n8n container
Run claude login
Use "Local" connection mode

🔑 Authentication

💰 Cheaper! Claude Code subscription costs less than API usage.

# Docker
docker exec -it container_name claude login

# SSH (on remote server)
claude login

# Local
claude login

Follow the browser prompts to authenticate.

Alternative: API Key

Using ANTHROPIC_API_KEY (not recommended)

⚠️ More expensive than subscription pricing

Set via environment variable:

export ANTHROPIC_API_KEY="your-api-key"

Or in Docker Compose:

environment:
  - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}

⚙️ Node Operations

Operation	Description	Use Case
Execute Prompt	Send a prompt and get a response	Direct AI interaction
Execute with Context	Include files as context	Code review, analysis
Continue Session	Continue last conversation	Multi-turn interactions
Resume Session	Resume specific session by ID	Continue after interruption

📝 Detailed Parameters

Execute Prompt

Prompt (required): Instruction for Claude Code
Model: Claude model to use
Options: Working directory, timeout, system prompt

Execute with Context

Prompt (required): Instruction for Claude Code
Context Files: File paths to include
Additional Directories: Directory paths

Continue / Resume Session

Prompt (required): Follow-up message
Session ID (resume only): Previous session ID

💡 Use Cases

🔍 MR/PR Code Review Agent

┌─────────────┐     ┌──────────────┐     ┌─────────────┐     ┌──────────────┐
│   GitLab    │────▶│  Get Diff &  │────▶│ Claude Code │────▶│    Post      │
│   Webhook   │     │    Files     │     │   Review    │     │   Comments   │
└─────────────┘     └──────────────┘     └─────────────┘     └──────────────┘

Workflow Steps

Trigger: GitLab/GitHub webhook on new MR/PR
Fetch: Get changed files and diff via API
Review: Claude Code with executeWithContext
- "Review this code. Check for bugs, security issues, suggest improvements."
Post: Send review comments back to GitLab/GitHub
Notify: Alert team via Slack/Discord (optional)

🎧 Support Assistant

┌─────────────┐     ┌──────────────┐     ┌─────────────┐     ┌──────────────┐
│   Support   │────▶│   Analyze    │────▶│ Claude Code │────▶│   Respond    │
│   Ticket    │     │    Issue     │     │   Solution  │     │   or Route   │
└─────────────┘     └──────────────┘     └─────────────┘     └──────────────┘

Workflow Steps

Trigger: Webhook from support system (Zendesk, Intercom)
Analyze: Claude Code understands the issue
- "User reports: [issue]. Analyze and suggest solution."
Respond: Send AI response back via API
Escalate: Route complex issues to humans

📚 Auto Documentation

┌─────────────┐     ┌──────────────┐     ┌─────────────┐     ┌──────────────┐
│    Code     │────▶│  Get Changed │────▶│ Claude Code │────▶│   Commit     │
│    Push     │     │    Files     │     │  Gen Docs   │     │    Docs      │
└─────────────┘     └──────────────┘     └─────────────┘     └──────────────┘

Workflow Steps

Trigger: Webhook on code push to main
Identify: Get list of changed files
Generate: Claude Code generates documentation
- "Generate docs for this code. Include descriptions, params, examples."
Commit: Create commit with updated docs
PR: Optionally create a PR for review

🐛 Auto Bug Fixing

┌─────────────┐     ┌──────────────┐     ┌─────────────┐     ┌──────────────┐
│   Sentry    │────▶│    Parse     │────▶│ Claude Code │────▶│  Create PR   │
│   Alert     │     │ Stack Trace  │     │   Fix Bug   │     │   + Notify   │
└─────────────┘     └──────────────┘     └─────────────┘     └──────────────┘

Workflow Steps

Trigger: Webhook from error monitoring (Sentry, Datadog)
Analyze: Parse error stack trace
Fix: Claude Code analyzes and fixes
- "Error: [stack trace]. Analyze code and provide a fix."
Test: Run tests to validate
PR: Create pull request with fix
Notify: Alert team about automated fix

🤖 Cloud Coding Bots

Build AI coding assistants on any platform:

📱 Telegram

User ──▶ Bot ──▶ Claude
              ──▶ Reply

💬 Slack

@bot ──▶ Fetch ──▶ Claude
              ──▶ Thread

🎮 Discord

!help ──▶ Parse ──▶ Claude
               ──▶ Embed

🦊 GitLab/GitHub

Comment ──▶ API ──▶ Claude
                ──▶ Reply

Example: Telegram Bot

Trigger: Telegram trigger on new message
Process: Claude Code handles coding question
Reply: Send response via Telegram node

Example: Slack Bot

Trigger: Slack mention or slash command
Context: Fetch relevant code from repos (optional)
Respond: Post response to channel

Example: GitLab/GitHub Bot

Trigger: Issue comment with keyword (e.g., /claude)
Analyze: Fetch issue context and code
Comment: Post Claude's analysis

📤 Output Structure

{
  "success": true,
  "sessionId": "550e8400-e29b-41d4-a716-446655440000",
  "output": "Here's my analysis of the code...",
  "exitCode": 0,
  "duration": 15234,
  "cost": 0.0523,
  "numTurns": 3,
  "usage": {
    "inputTokens": 1250,
    "outputTokens": 890
  }
}

Field	Description
`success`	✅ Execution completed successfully
`sessionId`	🔗 ID for continuing conversations
`output`	📝 Response text from Claude Code
`cost`	💰 Estimated cost in USD
`usage`	📊 Token breakdown

🔒 Security

🛡️ Tool Permissions

Control what Claude Code can do:

✅ Allowed: Read, Glob, Grep
❌ Blocked: Bash(rm:*), Write(.env)

🐳 Isolation

Use Docker containers
Mount only needed directories
Read-only mounts when possible

🔐 Recommended Security Settings

Disallow dangerous operations:

Bash(rm:*) - Prevent file deletion
Bash(sudo:*) - No sudo access
Write(.env) - Protect secrets
Bash(curl:*) - Block network (if not needed)

Isolation best practices:

Always set specific working directory
Avoid / or home directories
Create dedicated workspace per project

🤝 Contributing

Contributions welcome!

# 1. Fork the repo
# 2. Create feature branch
git checkout -b feature/amazing-feature

# 3. Commit changes
git commit -m 'feat: add amazing feature'

# 4. Push & create PR
git push origin feature/amazing-feature

📄 License

MIT License - see LICENSE for details.

GitHub • npm • n8n Community

Made with ❤️ for the n8n community