@frase/mcp-server

Use Claude Desktop to interact with your Frase account. This MCP (Model Context Protocol) server exposes Frase's API as tools that Claude can use to help you with SEO content creation, research, and optimization.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude to securely connect to external tools and data sources. This server implements MCP to give Claude access to your Frase account.

Quick Start

1. Get your API key

Get your API key from Frase Settings.

2. Configure Claude Desktop

Add this to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "frase": {
      "command": "npx",
      "args": ["-y", "@frase/mcp-server"],
      "env": {
        "FRASE_API_KEY": "sk_live_your_api_key_here"
      }
    }
  }
}

3. Restart Claude Desktop

After saving the config, restart Claude Desktop. You should see "frase" in the MCP servers list.

Available Tools

Sites

• list_sites - List all sites in your account

Briefs

• list_briefs - List content briefs with optional status filter
• create_brief - Create a new brief (with optional auto-outline generation)
• get_brief - Get brief details including outline and SERP data

Content

• list_content - List content items with optional status filter
• get_content - Get content details including full body text

Research

• list_research - List research sessions
• start_research - Start new AI-powered research on a topic

Jobs

• get_job_status - Check status of async jobs (briefs, research, audits, etc.)

Audits

• list_audits - List site audits
• start_audit - Start a new site audit
• get_audit - Get audit details with pages and issues
• export_audit - Export audit data as CSV

SERP Analysis

• analyze_serp - Analyze search engine results for a query
• analyze_competitors - Analyze competitor content for a query
• get_search_intent - Get search intent classification for a query

AI Visibility

• get_ai_visibility - Get AI visibility metrics for a site
• list_prompts - List monitored AI prompts
• create_prompt - Create a new monitored prompt
• get_prompt - Get prompt details with citations
• update_prompt - Update a monitored prompt
• get_competitors - Get AI visibility competitors
• get_alerts - Get AI visibility alerts
• get_insights - Get AI visibility insights

Analytics

• get_gsc_overview - Get Google Search Console overview metrics
• get_gsc_queries - Get top search queries from GSC
• get_gsc_pages - Get top performing pages from GSC
• get_content_gaps - Get content gap opportunities

Optimizations

• list_optimizations - List optimization sessions
• start_optimization - Start optimization analysis for content
• get_optimization - Get optimization details with suggestions
• apply_optimization - Apply optimization suggestions
• get_optimization_insights - Get optimization insights

Webhooks

• list_webhooks - List configured webhooks
• create_webhook - Create a new webhook
• get_webhook - Get webhook details
• update_webhook - Update a webhook
• delete_webhook - Delete a webhook

Example Conversations

List your sites

You: What sites do I have connected?
Claude: [Uses list_sites tool]

Here are your connected sites:

| Name | Domain | GSC | Created |
|------|--------|-----|---------|
| Main Blog | example.com | ✅ | Jan 15, 2024 |
| Product Site | product.example.com | ❌ | Feb 20, 2024 |

Create a brief with auto-outline

You: Create a brief about React performance optimization
Claude: [Uses create_brief with generate_outline=true]

## Brief Created

- **ID:** abc123
- **Topic:** React performance optimization
- **Status:** pending

**Outline generation started.** Let me check the status...

[Uses get_job_status]

The outline is ready! Let me get the details...

[Uses get_brief]

## Brief: React performance optimization

### Outline
- Introduction to React Performance
- Common Performance Bottlenecks
- Optimization Techniques
- Measuring Performance
- ...

Research a topic

You: Research best practices for Next.js SEO
Claude: [Uses start_research]

## Research Started

- **ID:** xyz789
- **Query:** best practices for Next.js SEO
- **Status:** pending

I'll check on the progress...

MCP Resources

Browse your Frase data directly in Claude Desktop:

• frase://sites - List all your sites
• frase://sites/{id} - View individual site details
• frase://content - List all content items
• frase://content/{id} - View content with full body
• frase://briefs - List all briefs
• frase://briefs/{id} - View brief with outline

MCP Prompts

Pre-built workflows for common SEO tasks:

Configuration

Development

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build
npm run build

# Run tests
npm test

# Run integration tests (requires FRASE_TEST_API_KEY)
npm run test:integration

Troubleshooting

Server not appearing in Claude Desktop

1. Verify your config file location:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Check JSON syntax - use a validator if needed

3. Restart Claude Desktop completely (quit and reopen)

Authentication errors

• Verify your API key is correct
• Ensure the key has not expired
• Check that the key has the required permissions

Debug mode

Enable debug logging to see detailed information:

{
  "mcpServers": {
    "frase": {
      "command": "npx",
      "args": ["-y", "@frase/mcp-server"],
      "env": {
        "FRASE_API_KEY": "your_key",
        "FRASE_MCP_DEBUG": "true"
      }
    }
  }
}

Rate limiting

The server automatically retries on rate limits with exponential backoff. If you're hitting limits frequently, consider spacing out your requests.

Support

• Frase Documentation
• API Documentation
• GitHub Issues

License

MIT