Cline — AI Coding Tool Guide
VS Code extension for autonomous AI coding. Browser automation, MCP server creation, terminal control, and prompt patterns for complex multi-step development workflows.
Cline
Cline is a VS Code extension that acts as an autonomous AI coding agent. It can read/write files, execute terminal commands, control a browser, and create/modify MCP servers — all from a chat interface inside VS Code.
What Makes Cline Different
- Browser automation — Opens a browser, navigates pages, clicks buttons, extracts data, and takes screenshots
- MCP server creation — Build custom MCP servers for your workflow from scratch
- Autonomous execution — Given a goal, Cline iterates autonomously through the full edit-build-test cycle
- VS Code native — Extension, no separate terminal. All context lives inside the editor
Getting Started
Install from the VS Code Marketplace. Configure your API key in extension settings.
Prompt Patterns
End-to-End API Development
Create a REST API for a task management app:
1. Set up Express.js with TypeScript
2. Add PostgreSQL with Prisma ORM
3. Create CRUD endpoints for tasks
4. Add input validation with zod
5. Generate OpenAPI documentation
6. Write integration tests
7. Run `npm test` to verify everything works
Browser Automation
Test the signup flow on our staging site:
1. Navigate to https://staging.example.com/signup
2. Fill the form with test data: name=Test User, [email protected]
3. Click submit
4. Check for success redirect to /dashboard
5. Take a screenshot of the result
6. Report any issues found
MCP Server Creation
Create an MCP server that queries our internal Jira instance:
1. Use the @modelcontextprotocol/sdk package
2. Create tools: search_issues, get_issue, create_issue
3. Authenticate via JIRA_API_TOKEN environment variable
4. Handle pagination for search results
5. Write a README with setup instructions
6. Test with `npx @modelcontextprotocol/inspector`
Multi-Service Integration
Set up a CI pipeline that:
1. Reads the PR diff from GitHub API
2. Runs only affected tests (detect via file paths)
3. Posts results as a PR comment
4. If tests pass, triggers a staging deploy via Vercel API
5. Sends a Slack notification to the team channel
Configuration
Cline settings in VS Code:
{
"cline.apiKey": "sk-ant-...",
"cline.model": "claude-sonnet-4-20250514",
"cline.autoApprove": false,
"cline.maxRequestsPerTask": 50,
"cline.browser.viewport": "1280x720"
}
MCP Configuration
Add MCP servers in Cline's settings panel (same format as Claude Code):
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}"
}
},
"playwright": {
"command": "npx",
"args": ["-y", "@anthropic/mcp-server-playwright"]
}
}
}
Related Pages
- Tool Comparison — Cline vs other autonomous coding tools
- MCP Section — Browse MCP servers (Cline can create and use these)
- Roo Code — Cline fork with specialized modes
- Agentic Prompting (Prompts) — Autonomous agent fundamentals
Related Articles
Prompt Engineering in Pi
Master prompt engineering for pi, the minimal terminal coding agent. Context files, system prompt files, slash commands, message queueing, and the four built-in tools.
OfficeCLI — An Office Suite Purpose-Built for AI Agents
OfficeCLI is the first open-source Office suite designed from the ground up for AI agents. Single binary, no Office installation required, with a built-in rendering engine that closes the create-view-fix loop autonomously. Here's why this fills a critical gap in enterprise agent tooling.
CLI-First Development with Antigravity Image Pipeline
Use fast CLI tools for all coding, then switch to Antigravity for Nano Banana image generation. Both under one Google AI Pro plan with no per-image fees.