JinaAI Reader

🔍 Model Context Protocol (MCP) tool for parsing websites using the Jina.ai Reader

javascript

30

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "spences10-mcp-jinaai-reader": {
      "command": "node",
      "args": [
        "-y",
        "mcp-jinaai-reader"
      ],
      "env": {
        "JINAAI_API_KEY": "your-jinaai-api-key"
      }
    }
  }
}

You can use this MCP server to extract and convert web content via Jina.ai Reader, then feed clean, structured text to your language model. It’s designed to handle documentation and diverse web content efficiently, making it easier to reason about and reference online material in prompts.

How to use

Configure your MCP client with the available MCP servers and then call the read_url tool to convert any URL into LLM-friendly text. You can tailor the extraction with selectors, timeouts, and summaries for links and images to suit your use case.

How to install

Prerequisites: ensure you have Node.js installed on your system. You will also need an API key for Jina.ai (JINAAI_API_KEY).

# 1) Install Node.js from the official site if you do not have it
# 2) Ensure npm is available

# 3) Set up a project directory and install dependencies if you are wrapping this server
# (Actual installation steps may vary depending on how you integrate MCP in your environment)

# 4) Run the server using the MCP command configuration examples when you want to start locally

Additional configuration and notes

The MCP server relies on the following configuration snippet to run as a local process. You can also run via a WSL-based workflow if you use Claude Desktop in a Windows environment.

MCP server configuration examples shown below define how to start the server and provide the required API key.

Configuration examples you can apply

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

Environment considerations

Set your Jina.ai API key in the environment to authorize access. The server requires the JINAAI_API_KEY variable to be present for both local and WSL-based configurations.

Security and usage tips

Keep your API key secret and avoid embedding it in shared command histories. When running in production, consider isolating the MCP server in a secure environment and rotating keys as needed.

Troubleshooting

If you encounter connectivity or extraction issues, verify that the Jina.ai API key is valid and that your MCP client is correctly configured to point to the jinaai-reader server. Check that the required environment variable is accessible in the running process.

Available tools

read_url

Converts a given URL into LLM-friendly text using Jina.ai Reader, with optional formatting, selectors, timeout, and summaries for links and images.