Jina Ai MCP Multimodal Search

🚀 Jina AI MCP Server

A Model Context Protocol (MCP) server that seamlessly integrates with Jina AI's neural search capabilities. This server offers semantic search, image search, and cross-modal search functions through a simple interface.

🚀 Quick Start

The Jina AI MCP Server provides an array of search functionalities, including semantic search, image search, and cross-modal search. It's designed to integrate smoothly with Jina AI's neural search features.

✨ Features

• Semantic Search: Use natural language queries to find semantically similar documents.
• Image Search: Search for visually similar images using an image URL.
• Cross-modal Search: Perform text-to-image or image-to-text searches.

📦 Installation

Prerequisites

• Node.js 16 or higher.
• A Jina AI account and API key (Get here).
• An MCP-compatible environment (e.g., Cline).

Steps

1. Clone the repository:

git clone <repository-url>
cd jina-ai-mcp

2. Install dependencies:

npm install

3. Create a .env file containing your Jina AI API key:

JINA_API_KEY=your_api_key_here

4. Build the server:

npm run build

🔧 Configuration

Add the following configuration to your MCP settings file:

{
  "mcpServers": {
    "jina-ai": {
      "command": "node",
      "args": [
        "/path/to/jina-ai-mcp/build/index.js"
      ],
      "env": {
        "JINA_API_KEY": "your_api_key_here"
      }
    }
  }
}

💻 Usage Examples

Basic Usage

1. Semantic Search

Perform semantic/neural search on text documents.

use_mcp_tool({
  server_name: "jina-ai",
  tool_name: "semantic_search",
  arguments: {
    query: "Search query text",
    collection: "your-collection-name",
    limit: 10 // Optional, default is 10
  }
})

2. Image Search

Search for similar images using an image URL.

use_mcp_tool({
  server_name: "jina-ai",
  tool_name: "image_search",
  arguments: {
    imageUrl: "https://example.com/image.jpg",
    collection: "your-collection-name",
    limit: 10 // Optional, default is 10
  }
})

3. Cross-modal Search

Perform text-to-image or image-to-text searches.

use_mcp_tool({
  server_name: "jina-ai",
  tool_name: "cross_modal_search",
  arguments: {
    query: "Beautiful sunset", // Or an image URL for image-to-text search
    mode: "text2image", // Or "image2text"
    collection: "your-collection-name",
    limit: 10 // Optional, default is 10
  }
})

Response Format

All search tools return results in the following format:

{
  content: [
    {
      type: "text",
      text: JSON.stringify({
        results: [
          {
            id: string,
            score: number,
            data: Record<string, any>
          }
        ]
      }, null, 2)
    }
  ]
}

🛡️ Error Handling

The server handles various error conditions, including:

• Invalid API keys.
• Missing or invalid parameters.
• API rate limits.
• Network errors.
• Invalid collection names.

All errors are returned in an appropriate format, along with the corresponding error code and message.

🤝 Contributing

Contributions are welcome! Please feel free to submit pull requests.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Jina AI: For providing powerful neural search capabilities.
• Community Contributors: Thank you for your support and feedback.