# Reviewing Code with MCP

Once Optibot MCP is installed and configured, you can run code reviews live inside your AI editor and watch them progress in real time — or integrate reviews into your CI/CD pipeline as an automated step.

## Watch Review Progress in Real Time

When you trigger a review (e.g., "review my local changes" or "review this branch"), Optibot streams the review progress back to your editor. You’ll see the review move through these stages:

| Stage                | What’s happening                                 |
| -------------------- | ------------------------------------------------ |
| `started`            | Review initiated — Optibot has received the code |
| `analyzing_patch`    | Optibot is parsing and structuring the diff      |
| `tool_call`         | Optibot is running analysis tools against the code |
| `generating_review`  | Findings are being compiled and written          |
| `completed`         | Review is finished — results are ready           |

Progress updates appear in real time in your editor so you always know where the review stands. For large diffs, this typically takes 30–90 seconds.

## CI/CD Integration

You can use the Optibot MCP tools in CI/CD pipelines by running `optibot-mcp` as a command-line tool with your API key.

### Setup

1. **Generate an API key** from your Optibot dashboard at [agents.getoptimal.ai](https://agents.getoptimal.ai/) → Settings → API Keys.
2. **Store the API key as a secret** in your CI provider:
   - GitHub Actions: Add it as a repository or organization secret named `OPTIBOT_API_KEY`.
   - GitLab CI: Add it under Settings → CI/CD → Variables.
   - Other providers: use the equivalent secrets/environment variable mechanism.
3. **Reference the secret** in your workflow YAML as an environment variable.

### GitHub Actions Example

```
name: Optibot Code Review

on:
  pull_request:
    branches: [main]

jobs:
  optibot-review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

- name: Install Optibot MCP
        run: npm install -g @optimalai/optibot-mcp

- name: Run Optibot Review
        env:
          OPTIBOT_API_KEY: ${{ secrets.OPTIBOT_API_KEY }}
        run: optibot-mcp review_branch
```

This runs a branch review on every pull request targeting `main`. Findings appear in the workflow run logs and, if Optibot’s GitHub integration is configured, are also posted as PR comments.

### Other CI Providers

The pattern is the same for any CI provider that supports environment variables:

1. Install: `npm install -g @optimalai/optibot-mcp`
2. Set `OPTIBOT_API_KEY` from your secrets store.
3. Run `optibot-mcp review_branch` (or `review_local_changes` if reviewing uncommitted changes).

### Environment Variables

| Variable                | Required | Description                                                      |
| ----------------------- | -------- | --------------------------------------------------------------- |
| `OPTIBOT_API_KEY`      | Yes      | Your Optibot API key for authentication                          |
| `OPTIBOT_API_URL`      | No       | Override the Optibot API endpoint (default: `https://api.getoptimal.ai`). Only needed for on-prem or custom deployments.