Xpath

An MCP server for executing XPath queries, supporting queries on XML/HTML content and queries on content obtained from a URL.

Developer tools Research and data #XPath query #XML processing #Web scraping .TypeScript

rating : 2 points

downloads : 10

update time : 2025-04-28

What is the XPath MCP Server?

The XPath MCP Server is a tool for executing XPath queries, which supports extracting the required data from XML or HTML content. It helps users easily locate and manipulate specific nodes in XML/HTML documents.

How to use the XPath MCP Server?

Through simple API calls, you can input XML/HTML content and XPath query expressions to quickly obtain the desired results.

Applicable scenarios

It is suitable for scenarios that require parsing and extracting data from XML or HTML documents, such as web crawlers, data cleaning, or content analysis.

Main features

XPath querySupports querying XML or HTML content using standard XPath syntax.

URL supportCan load XML or HTML content from a remote URL and execute queries.

Advantages and limitations

Advantages

It is easy to use and can complete data extraction without writing complex code.

Supports multiple MIME types (such as text/xml, application/xml, text/html, etc.).

It is open - source and free, and can be customized according to requirements.

Limitations

For very large XML files, performance may need to be optimized.

Does not support some advanced XPath features (such as namespace handling).

How to use

Install the XPath MCP Server

Quickly install it into your Claude Desktop environment via the Smithery CLI.

Configure the environment

Add relevant settings for the XPath MCP Server to the configuration file of Claude Desktop.

Execute a query

Call the API and pass the XML content and XPath query expression.

Usage examples

Query the values of all <item> elementsExtract the text values of all <item> elements from the given XML content.

Get all linksExtract all hyperlink addresses from an HTML document.

Frequently Asked Questions

How to install the XPath MCP Server?

Does it support namespace handling?

What if the XPath query returns an empty result?

Related resources

Official documentation

Detailed API documentation and technical instructions.

GitHub repository

Source code and the latest updates.

Example tutorial video

Watch a video guide on how to use the XPath MCP Server.

🚀 XPath MCP Server

An MCP server for executing XPath queries on XML content.

🚀 Quick Start

This is an MCP server designed to execute XPath queries on XML content. It offers two main tools for querying XML/HTML content either directly or from a URL.

✨ Features

Tools

xpath
- Query XML content using an XPath expression.
- Input:
  - xml (string): The XML content to be queried.
  - query (string): The XPath query to be executed.
  - 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 from which to fetch the XML/HTML content.
  - query (string): The XPath query to be executed.
  - 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 via Smithery for use with Claude Desktop:

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

# Install dependencies
npm install

# Build the package
npm run build

📚 Documentation

Setup

For Claude Desktop

Add the following to your claude_desktop_config.json:

Using npx

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

Using Node.js directly

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

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

💻 Usage Examples

Query XML content

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

Query HTML content

// Get the href attributes of all links
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

// Fetch content from a specified URL and query it
const result = await callTool("xpath", {
  url: "https://example.com/path/to/content.html",
  query: "//some/xpath/query",
  mimeType: "text/html"
});