> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vidnavigator.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Use natural language to interact with VidNavigator through Cursor and Claude Desktop

## VidNavigator MCP Server

The VidNavigator MCP (Model Context Protocol) Server enables you to search, analyze, and transcribe videos directly from your AI coding assistant. Available for both **Cursor** and **Claude Desktop**.

<CardGroup cols={2}>
  <Card title="AI Video Search" icon="magnifying-glass">
    Search for videos using natural language with advanced AI analysis and relevance ranking.
  </Card>

  <Card title="Video Analysis" icon="chart-mixed">
    Get comprehensive analysis of YouTube videos with summaries, key insights, and Q\&A.
  </Card>

  <Card title="Transcript Extraction" icon="file-text">
    Extract YouTube video transcripts quickly without full analysis.
  </Card>

  <Card title="Multi-Platform Transcription" icon="video">
    Transcribe videos from Instagram, TikTok, Facebook, and other social platforms.
  </Card>
</CardGroup>

## Quick Setup

### For Cursor Users

<Steps>
  <Step title="Get your API key">
    Visit [VidNavigator](https://vidnavigator.com) → User → Dev-tools to get your free API key.
  </Step>

  <Step title="Add MCP Server">
    Open Cursor → Settings → Tools and integration → Add MCP server, then paste:

    ```jsonc theme={null}
    {
      "mcpServers": {
        "vidnavigator": {
          "type": "http",
          "url": "https://api.vidnavigator.com/mcp/",
          "headers": {
            "Authorization": "Bearer YOUR_API_KEY_HERE"
          }
        }
      }
    }
    ```

    Replace `YOUR_API_KEY_HERE` with your actual API key.

    <img src="https://mintcdn.com/vidnavigator/-DcJASa3SliNkW2X/images/mcp/cursor-screenshot.png?fit=max&auto=format&n=-DcJASa3SliNkW2X&q=85&s=1f603f3664c17394dcab67253d436074" alt="Cursor MCP Configuration" width="3206" height="2018" data-path="images/mcp/cursor-screenshot.png" />
  </Step>

  <Step title="Start using">
    You can now ask questions like:

    * "Find a video where Neil deGrasse Tyson explains gravity"
    * "Summarize this YouTube video: [https://youtube.com/watch?v=xyz](https://youtube.com/watch?v=xyz)"
    * "What did the speaker say about climate policy?"
  </Step>
</Steps>

## Automate with n8n

You can integrate VidNavigator into your custom workflows with [n8n](https://n8n.io/), an open-source automation tool. This allows you to build powerful automations for searching, analyzing, and transcribing videos.

Watch this video to learn how to set up an n8n workflow that connects to the VidNavigator MCP server, and follow the steps below.

<div style={{ position: 'relative', paddingBottom: '56.25%', height: 0 }}>
  <iframe
    src="https://www.youtube.com/embed/mpzvCfIMaLo"
    frameBorder="0"
    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
    allowFullScreen
    style={{
  position: 'absolute',
  top: 0,
  left: 0,
  width: '100%',
  height: '100%',
}}
  />
</div>

<Steps>
  <Step title="Create n8n Workflow">
    Start by creating a new, empty workflow in your n8n instance.
  </Step>

  <Step title="Configure AI Agent">
    Add an **AI Agent** node. Inside the node, connect it to your preferred Large Language Model (LLM), such as OpenAI, and configure a memory option.
  </Step>

  <Step title="Add MCP Client">
    Add the native **MCP Client** tool from n8n. This client will connect to the VidNavigator MCP server, giving your workflow access to all the available video tools.
  </Step>

  <Step title="Set Server URL">
    In the MCP Client node, set the **Server URL** to `https://api.vidnavigator.com/mcp/` and ensure the transport is set to `HTTP Streamable Server`.
  </Step>

  <Step title="Authenticate Your Client">
    Generate a new API key from your [VidNavigator Dev Tools](https://vidnavigator.com/studio/api). In the MCP Client node, set up a header with the name `X-API-Key` and paste your API key as the value.
  </Step>

  <Step title="Connect and Use">
    Connect the MCP Client to the AI Agent. You can now send natural language prompts to the AI Agent to search, analyze, or transcribe any online video.
  </Step>
</Steps>

### For Claude Desktop Users

<Steps>
  <Step title="Download Extension">
    Download the latest extension from [GitHub Releases](https://github.com/vidnavigator/vidnavigator-mcp-starter/releases/latest) (`.dxt` file).
  </Step>

  <Step title="Get your API key">
    Visit [VidNavigator](https://vidnavigator.com) → User → Dev-tools to get your free API key.
  </Step>

  <Step title="Install Extension">
    Open Claude Desktop → Settings → Extensions → Install Extensions

    <img src="https://mintcdn.com/vidnavigator/-DcJASa3SliNkW2X/images/mcp/claude-screenshot-extensions.png?fit=max&auto=format&n=-DcJASa3SliNkW2X&q=85&s=14e2def503e7a7f45d48097bd1aa5386" alt="Claude Desktop Extensions" width="1265" height="997" data-path="images/mcp/claude-screenshot-extensions.png" />

    Select the downloaded `.dxt` file and follow the installation prompts.

    <img src="https://mintcdn.com/vidnavigator/-DcJASa3SliNkW2X/images/mcp/claude-screenshot-install.png?fit=max&auto=format&n=-DcJASa3SliNkW2X&q=85&s=076810f261f3033c22eb28cf81f5eac3" alt="Install Extension" width="757" height="895" data-path="images/mcp/claude-screenshot-install.png" />
  </Step>

  <Step title="Configure API Key">
    Configure your API key in the extension settings and enable the extension.

    <img src="https://mintcdn.com/vidnavigator/-DcJASa3SliNkW2X/images/mcp/claude-screenshot-enable.png?fit=max&auto=format&n=-DcJASa3SliNkW2X&q=85&s=0f0a34d560e4ca850718fb1a8b2ec8e4" alt="Enable Extension" width="762" height="885" data-path="images/mcp/claude-screenshot-enable.png" />
  </Step>

  <Step title="Start chatting">
    You can now interact with videos directly through Claude Desktop!
  </Step>
</Steps>

## Available Tools

<AccordionGroup>
  <Accordion title="search_videos">
    Search for videos with AI analysis and ranking using natural language queries.

    **Example**: "Find videos about React performance optimization"
  </Accordion>

  <Accordion title="analyze_video">
    Analyze video content and generate comprehensive summaries with key insights.

    **Example**: "Analyze this video: [https://youtube.com/watch?v=xyz](https://youtube.com/watch?v=xyz)"
  </Accordion>

  <Accordion title="get_video_transcript">
    Extract video transcripts quickly without full analysis.

    **Example**: "Get the transcript for this video: [https://youtube.com/watch?v=xyz](https://youtube.com/watch?v=xyz)"
  </Accordion>

  <Accordion title="transcribe_video">
    Transcribe non-YouTube videos from platforms like Instagram, TikTok, Facebook.

    **Example**: "Transcribe this TikTok video: [https://tiktok.com/@user/video/123](https://tiktok.com/@user/video/123)"
  </Accordion>

  <Accordion title="answer_followup_question">
    Ask specific questions about previously analyzed videos.

    **Example**: "What did the speaker say about the main challenges?"
  </Accordion>

  <Accordion title="get_usage">
    Check your API usage and subscription limits.

    **Example**: "How many API calls have I made this month?"
  </Accordion>
</AccordionGroup>

## Example Queries

Here are some example queries you can try with the MCP server:

<CodeGroup>
  ```text Video Search theme={null}
  "Find a video where Neil deGrasse Tyson explains gravity"
  ```

  ```text Video Analysis theme={null}
  "Summarize this YouTube video: https://youtube.com/watch?v=dQw4w9WgXcQ"
  ```

  ```text Transcript Extraction theme={null}
  "Give me the transcript for this video: https://youtube.com/watch?v=xyz"
  ```

  ```text Social Media Transcription theme={null}
  "Transcribe this TikTok video: [link]"
  ```

  ```text Follow-up Questions theme={null}
  "What did the speaker say about climate policy in the last video?"
  ```

  ```text Usage Tracking theme={null}
  "How many vidnavigator calls have I made this month?"
  ```
</CodeGroup>

## API Usage & Limits

All MCP server tools are subject to your [VidNavigator](https://vidnavigator.com) subscription plan:

* **Free Plan**: Limited requests per month
* **Paid Plans**: Higher limits based on plan tier

Use the `get_usage` tool to check your current usage and remaining limits at any time.

## Support

Need help with the MCP server setup or have questions?

<CardGroup cols={3}>
  <Card title="GitHub Repository" icon="github" href="https://github.com/vidnavigator/vidnavigator-mcp-starter">
    View source code and documentation
  </Card>

  <Card title="GitHub Issues" icon="github" href="https://github.com/vidnavigator/vidnavigator-mcp-starter/issues">
    Report bugs or request features
  </Card>

  <Card title="Postman Collection" icon="code" href="https://www.postman.com/vidnavigator/vidnavigator-ai/collection/68a216a90d896ae120e0ef4c">
    Test the MCP server API endpoints
  </Card>
</CardGroup>