Package Information
Documentation
_____ _ _ _____ _
/ ____| | | | / ____| | |
| | | | __ _ _ _ __| | ___ | | ___ __| | ___
| | | |/ _` | | | |/ _` |/ _ \ | | / _ \ / _` |/ _ \
| |____| | (_| | |_| | (_| | __/ | |___| (_) | (_| | __/
\_____|_|\__,_|\__,_|\__,_|\___| \_____\___/ \__,_|\___|
β‘ for n8n β‘
n8n-nodes-claude-code-cli
π€ Bring the power of Claude Code AI directly into your n8n workflows
Automate code reviews β’ Generate documentation β’ Fix bugs β’ Build coding bots
β¨ Features
| π³ Docker Execution - Run Claude Code in isolated containers | π Session Management - Multi-turn conversations across executions |
| π― Tool Permissions - Fine-grained control over allowed tools | π Context Files - Include files and directories for analysis |
| π§ Multiple Models - Opus, Sonnet, Haiku support | π Rich Output - Costs, tokens, and session IDs |
β‘ Quick Start
1. Install the n8n node
In n8n: Settings > Community Nodes > Install > n8n-nodes-claude-code-cli
2. Deploy Claude Code Runner
n8n installed on host (not in Docker)? Use the standalone setup:
mkdir -p claude-code-runner && cd claude-code-runner && \
curl -fsSL https://raw.githubusercontent.com/ThomasTartrau/n8n-nodes-claude-code-cli/main/docker/production/claude-code/docker-compose.yml -o docker-compose.yml && \
curl -fsSL https://raw.githubusercontent.com/ThomasTartrau/n8n-nodes-claude-code-cli/main/docker/production/claude-code/Dockerfile -o Dockerfile && \
docker compose up -d --build
n8n also running in Docker? Use the complete stack instead
The node uses docker exec to communicate with claude-code-runner. This requires:
- Docker CLI installed inside the n8n container
- Docker socket mounted to access the Docker daemon
The standard n8nio/n8n image doesn't include Docker CLI, so we provide a custom setup:
mkdir -p n8n-claude-code && cd n8n-claude-code && \
curl -fsSL https://raw.githubusercontent.com/ThomasTartrau/n8n-nodes-claude-code-cli/main/docker/production/n8n-with-claude-code/docker-compose.yml -o docker-compose.yml && \
curl -fsSL https://raw.githubusercontent.com/ThomasTartrau/n8n-nodes-claude-code-cli/main/docker/production/n8n-with-claude-code/Dockerfile.n8n -o Dockerfile.n8n && \
curl -fsSL https://raw.githubusercontent.com/ThomasTartrau/n8n-nodes-claude-code-cli/main/docker/production/n8n-with-claude-code/Dockerfile.claude-code -o Dockerfile.claude-code && \
docker compose up -d --build
This builds a custom n8n image with Docker CLI and deploys both n8n and claude-code-runner together. Access n8n at http://localhost:5678
Already have n8n running in Docker? You can modify your existing setup:
- Create a custom Dockerfile for n8n:
FROM docker:29-cli AS docker-cli
FROM n8nio/n8n
USER root
COPY --from=docker-cli /usr/local/bin/docker /usr/local/bin/docker
RUN chmod +x /usr/local/bin/docker
USER node
- Update your docker-compose.yml:
services:
n8n:
build: . # Use the custom Dockerfile above
user: root # Required for Docker socket access
volumes:
- /var/run/docker.sock:/var/run/docker.sock
# ... your other volumes
- Deploy claude-code-runner separately using the standalone setup above
Important: Both containers must be managed by the same Docker daemon.
3. Authenticate
docker exec -it claude-code-runner claude login
Follow the browser prompts to complete authentication.
4. Configure n8n credentials
| Parameter | Value |
|---|---|
| Connection Type | Docker |
| Container Name | claude-code-runner |
| Working Directory | /workspace |
5. Start automating π
Search "Claude Code" in n8n node panel and create your first workflow.
π³ Configuration
Workspace Setup
You have two options to work with your code:
Option 1: Clone repos inside container (recommended for isolation)
docker exec -it claude-code-runner git clone <repo-url>
# Or use git worktree for multiple branches
Option 2: Mount existing projects
volumes:
- /path/to/your/project:/workspace/project-name
MCP Servers
Mount your MCP configuration to enable additional tools:
volumes:
# MCP servers directory
- ./mcp-servers:/root/.mcp
# Or mount your local .mcp.json (avoids versioning credentials)
- ~/.mcp.json:/root/.mcp.json:ro
π Alternative: SSH deployment
For dedicated VM deployments (AWS EC2, GCP, etc.):
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt-get install -y nodejs git
npm install -g @anthropic-ai/claude-code
claude login
n8n Credentials:
| Parameter | Value |
|---|---|
| Connection Type | SSH |
| Host | Your VM IP |
| Port | 22 |
| Auth Method | privateKey |
βοΈ 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 |
π 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
π‘ Use Cases
π MR/PR Code Review Agent
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
β GitLab ββββββΆβ Get Diff & ββββββΆβ Claude Code ββββββΆβ Post β
β Webhook β β Files β β Review β β Comments β
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
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)
π§ Support Assistant
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
β Support ββββββΆβ Analyze ββββββΆβ Claude Code ββββββΆβ Respond β
β Ticket β β Issue β β Solution β β or Route β
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
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
π Auto Documentation
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
β Code ββββββΆβ Get Changed ββββββΆβ Claude Code ββββββΆβ Commit β
β Push β β Files β β Gen Docs β β Docs β
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
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
π Auto Bug Fixing
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
β Sentry ββββββΆβ Parse ββββββΆβ Claude Code ββββββΆβ Create PR β
β Alert β β Stack Trace β β Fix Bug β β + Notify β
βββββββββββββββ ββββββββββββββββ βββββββββββββββ ββββββββββββββββ
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
π€ Cloud Coding Bots
Build AI coding assistants on Telegram, Slack, Discord, or GitLab/GitHub.
Examples
π± Telegram Bot
- Trigger: Telegram trigger on new message
- Process: Claude Code handles coding question
- Reply: Send response via Telegram node
π¬ Slack Bot
- Trigger: Slack mention or slash command
- Context: Fetch relevant code from repos (optional)
- Respond: Post response to channel
π¦ GitLab/GitHub Bot
- Trigger: Issue comment with keyword (e.g.,
/claude) - Analyze: Fetch issue context and code
- Comment: Post Claude's analysis
π€ 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 |
β Execution completed successfully |
sessionId |
π ID for continuing conversations |
output |
π Response text from Claude Code |
cost |
π° Estimated cost in USD |
usage |
π Token breakdown |
π Security
π‘οΈ Tool Permissions
Control what Claude Code can do:
β
Allowed: Read, Glob, Grep
β Blocked: Bash(rm:*), Write(.env)
π³ Isolation Best Practices
- Always set specific working directory
- Avoid
/or home directories - Create dedicated workspace per project
π Recommended Security Settings
Disallow dangerous operations:
Bash(rm:*)- Prevent file deletionBash(sudo:*)- No sudo accessWrite(.env)- Protect secretsBash(curl:*)- Block network (if not needed)
π€ Contributing
Development Setup
git clone https://github.com/ThomasTartrau/n8n-nodes-claude-code-cli.git
cd n8n-nodes-claude-code-cli
npm install && npm run build
# Start n8n + claude-code-runner for testing
docker compose -f docker/development/docker-compose.yml up -d --build
# Authenticate claude-code-runner
docker exec -it claude-code-runner claude login
# Access n8n at http://localhost:5678
Docker Files Structure
docker/
βββ development/
β βββ Dockerfile # n8n with docker CLI (dev)
β βββ docker-compose.yml # n8n + claude-code-runner (mounts dist/)
βββ production/
βββ claude-code/
β βββ Dockerfile # Standalone claude-code-runner
β βββ docker-compose.yml # For n8n on host (not Docker)
βββ n8n-with-claude-code/
βββ Dockerfile.n8n # n8n with Docker CLI
βββ Dockerfile.claude-code # claude-code-runner
βββ docker-compose.yml # Complete stack (both services)
Submit Changes
git checkout -b feature/amazing-feature
git commit -m 'feat: add amazing feature'
git push origin feature/amazing-feature
π License
MIT License - see LICENSE for details.