Fan-Out MCP

Advanced content gap analysis for the AI search era

Analyze your content to discover what user queries it covers (and misses) using the same techniques AI search engines use internally.

Quick Navigation

Why this matters | What it does | Installation | How to use | Methodology | Features deep-dive | Parameters | Troubleshooting

Why This Matters

The problem: Traditional SEO focused on keywords and backlinks. AI search engines (ChatGPT, Perplexity, Gemini) don't work that way. They evaluate whether your content can answer user queries - across dozens of query variations you've probably never considered.

The solution: This MCP uses research-backed techniques from Google and academic papers to:

1. Decompose complex topics into the actual questions users ask
2. Generate query variations using Google's patented fan-out methodology
3. Assess whether your content can answer each query (with evidence)
4. Identify specific gaps and provide actionable recommendations

The result: Content optimized for Generative Engine Optimization (GEO) - answering the queries AI search engines need to cite your work.

What It Does

Three Analysis Modes

1. Content-Only Analysis (Default) Analyzes what questions your content naturally answers based on structure and topics.

Analyze https://your-site.com/article with standard depth

2. Hybrid Analysis (Content + Keyword Targeting) Combines content analysis with keyword-specific query variants. This is the power mode.

Analyze https://your-site.com/article with target_keyword "direct drive racing wheels"

Generates 15-25 query variants by default across 5 types:

• Equivalent - "sim racing wheels", "racing simulator wheels"
• Specification - "Fanatec DD Pro review", "8Nm direct drive wheel"
• Follow-Up - "how to calibrate racing wheel", "mounting options"
• Comparison - "Fanatec vs Thrustmaster", "belt drive vs direct drive"
• Clarification - "what is direct drive technology", "how does FFB work"

3. Keyword-Only Analysis Focus purely on keyword variants, skip content inference (50% faster).

Analyze https://your-site.com/article with target_keyword "sim racing" and fan_out_only true

The Output

Interactive visual dashboard showing:

• Coverage score (0-100) with specific gaps identified
• Query-by-query assessment with evidence quotes
• Prioritized recommendations (what to add/improve)
• Technical metrics (quality scores, performance data)

Plus detailed markdown report with all data.

Installation

Prerequisites

• Claude Desktop (or any MCP-compatible client)
• Anthropic API key
• Node.js 18+ (for local build only)

Quick Setup (Recommended)

The fastest way to get started - no cloning or building required:

1. Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fanout": {
      "command": "npx",
      "args": ["-y", "@houtini/fanout-mcp@latest"],
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-api03-your-key-here"
      }
    }
  }
}

Config file locations:

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

3. Restart Claude Desktop

Claude Code (CLI)

Claude Code uses a different registration mechanism -- it doesn't read claude_desktop_config.json. Use claude mcp add instead:

claude mcp add -e ANTHROPIC_API_KEY=sk-ant-... -s user fanout -- npx -y @houtini/fanout-mcp@latest

Verify with:

claude mcp get fanout

You should see Status: Connected.

4. Verify installation:

List available tools

You should see fanout:analyze_content_gap in the output.

How to Use

Basic Analysis

Analyze https://example.com/article for query coverage gaps

Claude will create an interactive dashboard showing:

• What queries your content covers
• What queries are partially covered
• What queries are missing (gaps)
• Specific recommendations for each gap

Keyword-Targeted Analysis

When to use: You're optimizing for a specific keyword or topic.

Analyze https://example.com/sim-racing-guide with target_keyword "sim racing wheels"

This generates 15-25 query variants related to your keyword and checks coverage for each. Perfect for:

• SEO + GEO optimization
• Ensuring you cover all keyword variations
• Finding specific gaps in keyword targeting

Advanced Options

Focus on specific area:

Quick analysis of https://example.com/pricing focusing on "enterprise plans"

Comprehensive deep-dive:

Comprehensive analysis of https://example.com/installation-guide

Custom variant types:

{
  "url": "https://example.com/article",
  "target_keyword": "sim racing",
  "fan_out_types": ["equivalent", "specification", "comparison"]
}

Context signals for smarter variants:

{
  "url": "https://example.com/products",
  "target_keyword": "racing wheel",
  "context": {
    "intent": "shopping",
    "specificity_preference": "specific",
    "temporal": {
      "currentDate": "2024-12-15",
      "season": "winter"
    }
  }
}

Understanding the Methodology

Based on Research

This tool implements techniques from cutting-edge Information Retrieval research:

Query Fan-Out - Based on Google's patented methodology (US 11663201 B2) and research paper Training Query Fan-Out Models with Generative Neural Networks. Generates query variants across 8 types to discover how users actually search for information.

Self-RAG - Self-Reflective Retrieval-Augmented Generation validates coverage with evidence. No hallucinations - every "covered" claim includes exact quotes from your content.

Query Decomposition - Least-to-Most prompting breaks complex topics into prerequisite, core, and follow-up queries.

Want to understand the research? 📖 Read our accessible explainer:

Understanding Keyword Fan-Out: The Research Explained

This document explains:

• Why query fan-out matters for content optimization
• How Google's methodology works (in plain language)
• Our adaptation using Claude Sonnet 4.5
• Real examples from testing
• When to use which variant types

For implementation details, see research/google-fanout-adaptation.md.

Features Deep-Dive

Keyword Fan-Out Variants

Default: 5 Variant Types (most actionable)

1. Equivalent (3-5 variants) - Alternative phrasings with same intent

   • "sim racing wheel" → "racing simulator wheel", "sim rig controller"

2. Specification (3-5 variants) - More specific versions with details

   • "sim racing wheel" → "Fanatec DD Pro wheel review", "direct drive 8Nm wheel"

3. Follow-Up (3-5 variants) - Logical next questions

   • "sim racing wheel" → "how to calibrate wheel", "best pedals for wheel"

4. Comparison (3-5 variants) - "Vs" and alternatives

   • "Fanatec vs Thrustmaster wheels", "direct drive vs belt driven"

5. Clarification (2-3 variants) - Understanding questions

   • "what is direct drive technology", "how does force feedback work"

Optional: 3 Additional Types (request via fan_out_types parameter)

6. Generalization - Broader encompassing queries
7. Related Aspects - Connected topics and implicit needs
8. Temporal - Time-specific versions with date qualifiers

Why 5 by default? These 5 types generate the most actionable, realistic queries users actually type. The other 3 are available but tend to:

• Drift off-topic (generalization, related aspects)
• Require explicit temporal context (temporal)

Want all 8 types?

{
  "target_keyword": "your keyword",
  "fan_out_types": ["equivalent", "specification", "generalization", "followUp", "comparison", "clarification", "relatedAspects", "temporal"]
}

Context-Aware Variant Generation

Provide context signals to guide more relevant variants:

Shopping Intent:

{
  "context": {
    "intent": "shopping",
    "specificity_preference": "specific"
  }
}

Generates: "where to buy X", "X Black Friday deals", "best budget X 2024"

Temporal Context:

{
  "context": {
    "temporal": {
      "currentDate": "2024-12-15",
      "season": "winter"
    }
  }
}

Generates: "X 2024", "new X December 2024", "latest X winter 2024"

Research Intent:

{
  "context": {
    "intent": "research",
    "specificity_preference": "balanced"
  }
}

Generates: "how does X work", "X comparison guide", "X vs Y detailed analysis"