MCP Jina Ai

🚀 Jina AI MCP Server

An MCP server that provides access to Jina AI's powerful network services via Claude. This server implements three main tools:

• Webpage reading and content extraction
• Web search
• Fact checking/location

✨ Features

Tools

read_webpage

• Extract content from webpages in a format suitable for LLMs.
• Support multiple output formats (default, Markdown, HTML, text, screenshot, Pageshot).
• Optionally include links and images.
• Automatically generate image description text.
• Cache control options.

search_web

• Conduct web searches using Jina AI's search API.
• The number of results is configurable (default: 5).
• Support image retention and description text generation.
• Support multiple return formats (Markdown, text, HTML).
• Structured results, including titles, descriptions, and content.

fact_check

• Perform fact checking using Jina AI's location engine.
• Provide a truthfulness score and supporting evidence.
• Optionally use the deep mode for a more comprehensive analysis.
• Return citation information, including key excerpts and their support/contradiction classifications.

📦 Installation

Prerequisites

Using this server requires a Jina AI API key. Get one for free at https://jina.ai/.

Installation Methods

There are two ways to use this server:

Install via Smithery (Recommended)

Automatically install Jina AI for Claude Desktop through Smithery:

npx -y @smithery/cli install jina-ai-mcp-server --client claude

Option 1: Use NPX (Recommended)

Add the following configuration to your Claude Desktop configuration file:

{
  "mcpServers": {
    "jina-ai-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "jina-ai-mcp-server"
      ],
      "env": {
        "JINA_API_KEY": "<YOUR_KEY>"
      }
    }
  }
}

Option 2: Local Installation

1. Clone the repository.
2. Install dependencies:

npm install

3. Build the server:

npm run build

4. Add the following configuration to your Claude Desktop configuration file:

{
  "mcpServers": {
    "jina-ai-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/jina-ai-mcp-server/dist/index.js"
      ],
      "env": {
        "JINA_API_KEY": "<YOUR_KEY>"
      }
    }
  }
}

Configuration File Location

On MacOS:

~/Library/Application Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Debugging

Since the MCP server communicates via standard input and output, debugging can be challenging. We recommend using MCP Inspector:

npm run inspector

The Inspector will provide a URL to access browser debugging tools.

📚 API Response Types

All tools return structured JSON responses, which include:

• Status codes and relevant information.
• Request IDs to track requests.
• Result data varies depending on the specific function. Ensure you correctly parse these responses for use in your application.