mcp jinaai search

Local 2025-08-31 23:31:12 0
search @spences10/mcp-jinaai-search

Enables efficient web search integration with Jina.ai's Search API, offering clean, LLM-optimized content retrieval with support for various content types and configurable caching.

⚠️ Notice

This repository is no longer maintained.

The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.

Please use mcp-omnisearch instead.

A Model Context Protocol (MCP) server for integrating Jina.ai's Search API with LLMs. This server provides efficient and comprehensive web search capabilities, optimised for retrieving clean, LLM-friendly content from the web.

Features

  • ? Advanced web search through Jina.ai Search API
  • ? Fast and efficient content retrieval
  • ? Clean text extraction with preserved structure
  • ? Content optimised for LLMs
  • ? Support for various content types including documentation
  • ?️ Built on the Model Context Protocol
  • ? Configurable caching for performance
  • ?️ Optional image and link gathering
  • ? Localisation support through browser locale
  • ? Token budget control for response size

Configuration

This server requires configuration through your MCP client. Here are examples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

{
    "mcpServers": {
        "jinaai-search": {
            "command": "node",
            "args": ["-y", "mcp-jinaai-search"],
            "env": {
                "JINAAI_API_KEY": "your-jinaai-api-key"
            }
        }
    }
}

Claude Desktop with WSL Configuration

For WSL environments, add this to your Claude Desktop configuration:

{
    "mcpServers": {
        "jinaai-search": {
            "command": "wsl.exe",
            "args": [
                "bash",
                "-c",
                "JINAAI_API_KEY=your-jinaai-api-key npx mcp-jinaai-search"
            ]
        }
    }
}

Environment Variables

The server requires the following environment variable:

  • JINAAI_API_KEY: Your Jina.ai API key (required)

API

The server implements a single MCP tool with configurable parameters:

Search the web and get clean, LLM-friendly content using Jina.ai Reader. Returns top 5 results with URLs and clean content.

Parameters:

  • query (string, required): Search query
  • format (string, optional): Response format ("json" or "text"). Defaults to "text"
  • no_cache (boolean, optional): Bypass cache for fresh results. Defaults to false
  • token_budget (number, optional): Maximum number of tokens for this request
  • browser_locale (string, optional): Browser locale for rendering content
  • stream (boolean, optional): Enable stream mode for large pages. Defaults to false
  • gather_links (boolean, optional): Gather all links at the end of response. Defaults to false
  • gather_images (boolean, optional): Gather all images at the end of response. Defaults to false
  • image_caption (boolean, optional): Caption images in the content. Defaults to false
  • enable_iframe (boolean, optional): Extract content from iframes. Defaults to false
  • enable_shadow_dom (boolean, optional): Extract content from shadow DOM. Defaults to false
  • resolve_redirects (boolean, optional): Follow redirect chains to final URL. Defaults to true

Development

Setup

  1. Clone the repository
  2. Install dependencies:
pnpm install
  1. Build the project:
pnpm run build
  1. Run in development mode:
pnpm run dev

Publishing

  1. Create a changeset:
pnpm changeset
  1. Version the package:
pnpm version
  1. Build and publish:
pnpm release

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

[
  {
    "description": "Search the web and get clean, LLM-friendly content using Jina.ai Reader. Returns top 5 results with URLs and clean content.",
    "inputSchema": {
      "properties": {
        "browser_locale": {
          "description": "Browser locale for rendering content",
          "type": "string"
        },
        "enable_iframe": {
          "default": false,
          "description": "Extract content from iframes",
          "type": "boolean"
        },
        "enable_shadow_dom": {
          "default": false,
          "description": "Extract content from shadow DOM",
          "type": "boolean"
        },
        "format": {
          "default": "text",
          "description": "Response format (json or text)",
          "enum": [
            "json",
            "text"
          ],
          "type": "string"
        },
        "gather_images": {
          "default": false,
          "description": "Gather all images at the end of the response",
          "type": "boolean"
        },
        "gather_links": {
          "default": false,
          "description": "Gather all links at the end of the response",
          "type": "boolean"
        },
        "image_caption": {
          "default": false,
          "description": "Caption images in the content",
          "type": "boolean"
        },
        "no_cache": {
          "default": false,
          "description": "Bypass cache for fresh results",
          "type": "boolean"
        },
        "query": {
          "description": "Search query",
          "type": "string"
        },
        "resolve_redirects": {
          "default": true,
          "description": "Follow redirect chains to final URL",
          "type": "boolean"
        },
        "stream": {
          "default": false,
          "description": "Enable stream mode for large pages",
          "type": "boolean"
        },
        "token_budget": {
          "description": "Maximum number of tokens for this request",
          "minimum": 1,
          "type": "number"
        }
      },
      "required": [
        "query"
      ],
      "type": "object"
    },
    "name": "search"
  }
]