Xpath

An MCP server for executing XPath queries, supporting local XML and remote URL content queries.

Developer tools Research and data #XPath Query #XML Processing #Web Scraping #Content Parsing Remote .JavaScript

rating : 2 points

downloads : 8.1K

update time : 2025-04-28

Open Site

What is the XPath MCP Server?

The XPath MCP Server is a tool that allows users to query XML or HTML content through XPath expressions. It helps developers easily extract and analyze structured data.

How to use the XPath MCP Server?

By calling specific API interfaces, you can input XML/HTML content and XPath query statements to obtain the desired results.

Applicable Scenarios

Suitable for scenarios where information needs to be extracted from structured data (such as XML or HTML), such as web crawlers and data analysis.

Main Features

XPath Query Tool

Allows users to input XML content and execute XPath queries, returning matching results.

URL Data Query Tool

Can fetch content from a remote URL and execute XPath queries.

Advantages

Supports multiple data sources (local files, URLs)

Easy to use, no complex programming knowledge required

Limitations

May not work properly for non-standard XML/HTML

Performance depends on network speed and data volume

How to Use

Install the Server

Quickly install via Smithery CLI, or manually clone the code and run it.

Configure the Client

Add MCP server configuration to claude_desktop_config.json.

Execute a Query

Call the API interface and pass in parameters, such as XML content and an XPath query.

Usage Examples

Query all item nodes in XML

Extract all item elements from an XML string.

Get all links from an HTML page

Extract all hyperlink addresses from an HTML page.

Frequently Asked Questions

Does the XPath MCP Server support JSON - formatted data?

How to ensure the accuracy of XPath queries?

Related Resources

Official Documentation

Detailed technical documentation and API reference.

GitHub Repository

Source code and latest version releases.

🚀 XPath MCP Server

An MCP server for executing XPath queries on XML content.

✨ Features

Tools

xpath
- Query XML content using an XPath expression.
- Input:
  - xml (string): The XML content to query.
  - query (string): The XPath query to execute.
  - mimeType (optional, string): The MIME type (e.g., text/xml, application/xml, text/html, application/xhtml+xml).
- Return: The result of the XPath query as a string.
xpathwithurl
- Fetch content from a URL and query it using an XPath expression.
- Input:
  - url (string): The URL to fetch the XML/HTML content from.
  - query (string): The XPath query to execute.
  - mimeType (optional, string): The MIME type (e.g., text/xml, application/xml, text/html, application/xhtml+xml).
- Return: The result of the XPath query as a string.

📦 Installation

Install via Smithery

To automatically install mcp-xpath for Claude Desktop, visit Smithery:

npx -y @smithery/cli install @thirdstrandstudio/mcp-xpath --client claude

# Install dependencies
npm install

# Build the package
npm run build

📚 Documentation

Setup

Use with Claude Desktop

Add the following to claude_desktop_config.json:

npx

{
  "mcpServers": {
    "xpath": {
      "command": "npx",
      "args": [
        "@thirdstrandstudio/mcp-xpath"
      ]
    }
  }
}

Use Node.js directly

{
  "mcpServers": {
    "xpath": {
      "command": "node",
      "args": [
        "/path/to/mcp-xpath/dist/index.js"
      ]
    }
  }
}

Replace /path/to/mcp-xpath with the actual repository path.

💻 Usage Examples

Query XML Content

// Select all <item> elements in the XML
const result = await callTool("xpath", {
  xml: "<root><item>value1</item><item>value2</item></root>",
  query: "//item/text()",
  mimeType: "text/xml"
});

Query HTML Content

// Get all links in the HTML
const result = await callTool("xpath", {
  xml: "<html><body><a href='link1.html'>Link 1</a><a href='link2.html'>Link 2</a></body></html>",
  query: "//a/@href",
  mimeType: "text/html"
});

Query URL Content

// Get all links on the web page
const result = await callTool("xpathwithurl", {
  url: "https://example.com",
  query: "//a/@href",
  mimeType: "text/html"
});

🔧 Technical Details

Development

# Install dependencies
npm install

# Start the server in development mode
npm start

📄 License

This MCP server is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, see the LICENSE file in the project repository.