Skip to main content
Configure Windsurf’s Cascade AI assistant to help you write and maintain documentation. This guide shows how to set up Windsurf specifically for your Mintlify documentation workflow.

​
Whawit MCP Integration

Connect Windsurf to Whawit for AI-assisted observability analysis. The Whawit MCP server gives Windsurf’s Cascade AI access to your logs, incidents, and project knowledge base.

​
Setup

Add to your Windsurf MCP configuration: 
{
  "mcpServers": {
    "WHAWIT": {
      "url": "https://mcp.whawit.ai/sse",
      "headers": {
        "X-API-Key": "YOUR_WHAWIT_API_KEY"
      }
    }
  }
}
Get your API key from the Whawit web app under Settings > User Settings.

​
Available Tools

Once configured, Windsurf can use these Whawit tools:
ToolDescription
whawit_context_searchSearch project knowledge base
whawit_devops_analysisAnalyze logs and metrics
whawit_project_infoGet project details
whawit_list_projectsList available projects
whawit_get_analysis_fullGet complete analysis data
whawit_get_incident_fullGet incident details
whawit_generate_fix_promptGenerate fix prompts
whawit_codebase_analysis_promptGenerate analysis prompts

​
Example Prompts

After connecting, try these prompts in Windsurf: 
What Redis errors occurred in my backend project in the last hour?

Search the knowledge base for how the payment flow works

Get the latest critical incident and suggest a fix
See the full MCP Server documentation for detailed tool schemas and configuration options.

​
Prerequisites

  • Windsurf editor installed
  • Access to your documentation repository

​
Workspace rules

Create workspace rules that provide Windsurf with context about your documentation project and standards. Create .windsurf/rules.md in your project root: 
# Mintlify technical writing rule

## Project context

- This is a documentation project on the Mintlify platform
- We use MDX files with YAML frontmatter  
- Navigation is configured in `docs.json`
- We follow technical writing best practices

## Writing standards

- Use second person ("you") for instructions
- Write in active voice and present tense
- Start procedures with prerequisites
- Include expected outcomes for major steps
- Use descriptive, keyword-rich headings
- Keep sentences concise but informative

## Required page structure

Every page must start with frontmatter:

```yaml
---
title: "Clear, specific title"
description: "Concise description for SEO and navigation"
---
```

## Mintlify components

### Callouts

- `<Note>` for helpful supplementary information
- `<Warning>` for important cautions and breaking changes
- `<Tip>` for best practices and expert advice  
- `<Info>` for neutral contextual information
- `<Check>` for success confirmations

### Code examples

- When appropriate, include complete, runnable examples
- Use `<CodeGroup>` for multiple language examples
- Specify language tags on all code blocks
- Include realistic data, not placeholders
- Use `<RequestExample>` and `<ResponseExample>` for API docs

### Procedures

- Use `<Steps>` component for sequential instructions
- Include verification steps with `<Check>` components when relevant
- Break complex procedures into smaller steps

### Content organization

- Use `<Tabs>` for platform-specific content
- Use `<Accordion>` for progressive disclosure
- Use `<Card>` and `<CardGroup>` for highlighting content
- Wrap images in `<Frame>` components with descriptive alt text

## API documentation requirements

- Document all parameters with `<ParamField>` 
- Show response structure with `<ResponseField>`
- Include both success and error examples
- Use `<Expandable>` for nested object properties
- Always include authentication examples

## Quality standards

- Test all code examples before publishing
- Use relative paths for internal links
- Include alt text for all images
- Ensure proper heading hierarchy (start with h2)
- Check existing patterns for consistency