Integrations

Connect POC.ai with your editor, AI coding agents, and CI/CD pipelines for seamless deployment workflows.

MCP Server

POC.ai ships as a Model Context Protocol (MCP) server, allowing any MCP-compatible AI agent to deploy code directly. The MCP server exposes tools for detection, deployment, status checking, and promotion.

Setup

Add the POC.ai MCP server to your MCP client configuration file:

{
  "mcpServers": {
    "poc-ai": {
      "command": "npx",
      "args": ["-y", "@poc-ai/mcp-server"],
      "env": {
        "POC_API_TOKEN": "poc_your_api_token_here"
      }
    }
  }
}

Available MCP tools

Tool	Description
`poc_detect`	Detect framework and generate deployment recipe
`poc_deploy`	Deploy a project and return preview URL
`poc_status`	Check deployment status
`poc_promote`	Promote preview to production
`poc_rollback`	Rollback to a previous version
`poc_logs`	Retrieve build and runtime logs

Claude Code

Claude Code can use the POC.ai MCP server to deploy projects during a coding session. Once configured, Claude can detect frameworks, deploy previews, and promote to production in the conversation flow.

Setup

Install the MCP server globally: npm install -g @poc-ai/mcp-server
Add the server to your Claude Code MCP configuration at ~/.claude/mcp_servers.json:

{
  "poc-ai": {
    "command": "npx",
    "args": ["-y", "@poc-ai/mcp-server"],
    "env": {
      "POC_API_TOKEN": "poc_your_api_token_here"
    }
  }
}

Restart Claude Code. The POC.ai tools will appear in the available tools list.

Example usage

In a Claude Code session, you can ask:

"Deploy this project to a preview URL"
"Check the status of my last deployment"
"Promote dep_7xk2m9 to production"

Cursor

Cursor supports MCP servers natively. Add POC.ai to your Cursor MCP config to enable deployment commands from within the editor.

Setup

Open Cursor Settings → MCP Servers
Add a new server with the following configuration:

{
  "mcpServers": {
    "poc-ai": {
      "command": "npx",
      "args": ["-y", "@poc-ai/mcp-server"],
      "env": {
        "POC_API_TOKEN": "poc_your_api_token_here"
      }
    }
  }
}

Save and restart Cursor. You can now ask Cursor's AI to deploy your project using POC.ai.

Tip: Store your API token in a .env file or system keychain instead of hardcoding it in the configuration.

VS Code Extension

The POC.ai VS Code extension adds a sidebar panel and command palette integration for deploying directly from the editor.

Installation

Open the Extensions panel in VS Code (Cmd+Shift+X / Ctrl+Shift+X)
Search for POC.ai
Click Install
Open the command palette (Cmd+Shift+P) and run POC.ai: Login

Commands

Command	Description
`POC.ai: Deploy`	Deploy the current workspace
`POC.ai: Status`	Check deployment status in the sidebar
`POC.ai: Promote`	Promote a preview to production
`POC.ai: Rollback`	Rollback to the previous version
`POC.ai: Logs`	Open deployment logs in the output panel

GitHub Actions

Automate deployments on every push or pull request using the official POC.ai GitHub Action.

Workflow setup

Create a workflow file at .github/workflows/poc-deploy.yml:

name: Deploy with POC.ai

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

jobs:
  deploy:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install POC.ai CLI
        run: npm install -g @poc-ai/cli

      - name: Deploy preview
        if: github.event_name == 'pull_request'
        run: poc deploy . --env preview --yes
        env:
          POC_API_TOKEN: ${{ secrets.POC_API_TOKEN }}

      - name: Deploy production
        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
        run: poc deploy . --env production --yes
        env:
          POC_API_TOKEN: ${{ secrets.POC_API_TOKEN }}

      - name: Comment preview URL
        if: github.event_name == 'pull_request'
        uses: actions/github-script@v7
        with:
          script: |
            github.rest.issues.createComment({
              issue_number: context.issue.number,
              owner: context.repo.owner,
              repo: context.repo.repo,
              body: 'Preview deployed! Check the POC.ai dashboard for the URL.'
            })

Required secrets

Secret	Description
`POC_API_TOKEN`	Your POC.ai API token. Add it in repo Settings → Secrets → Actions.

Tip: Use separate API tokens for CI and local development. Revoke CI tokens independently if compromised.

Next steps

Set up approval gates for team deployments in Team & Governance.
Learn about all CLI flags in the CLI Reference.