Jina_fetch

by RoadMillion

134 downloads
Not rated
GitHub

About

Convert url to LLM-friendly text, powered by jina ai reader

Details

Author
RoadMillion
Downloads
134
Categories
Automation

- Converts URLs into LLM-friendly text
- Uses Jina AI's URL reader API
- Single tool with one required parameter
- Standard MCP server for easy integration
- Supports development and published deployment

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Jina_fetch
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install by adding the server configuration to your Claude Desktop config file (MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%/Claude/claude_desktop_config.json). Use the reader tool with a mandatory url string parameter to process a URL and return its content.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "jina_fetch": {
            "jina_fetch": {
                "isActive": true,
                "command": "uvx",
                "args": [
                    "mcp-jina-reader@latest"
                ]
            }
        }
    }
}

McpServers

{
    "jina_fetch": {
        "isActive": true,
        "command": "uvx",
        "args": [
            "mcp-jina-reader@latest"
        ]
    }
}

mcp-jina-reader MCP server

A standard MCP server that converts URLs into LLM-friendly inputs using Jina AI's API

Tools

The server implements one tool:
- reader: Use Jina URL reader to process URLs and return LLM-friendly output
- Requires "url" as a mandatory string parameter
- Returns processed URL content

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

<details>
<summary>Development/Unpublished Servers Configuration</summary>

  "mcpServers": {
"mcp-jina-reader": {
"command": "uv",
"args": [
"--directory",
"your-dir",
"run",
"mcp-jina-reader"
]
}
}

</details>

<details>
<summary>Published Servers Configuration</summary>

  "mcpServers": {
"mcp-jina-reader": {
"command": "uvx",
"args": [
"mcp-jina-reader"
]
}
}

</details>

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token: --token or UV_PUBLISH_TOKEN
- Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory yourdir run mcp-jina-reader

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.