Encara en anglès — la traducció arribarà aviat.
XPath MCP Server - MCP Server segur per ALMC Security 2025

XPath MCP Server

Veure a GitHub

XPath MCP Server

Third Strand Studio

MCP Server for executing XPath queries on XML content.

image

smithery badge

Tools

  1. xpath

    • Query XML content using XPath expressions
    • Inputs:
      • 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)
    • Returns: The result of the XPath query as a string
  2. xpathwithurl

    • Fetch content from a URL and query it using XPath expressions
    • Inputs:
      • url (string): The URL to fetch 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)
    • Returns: The result of the XPath query as a string

Installation

Installing via Smithery

To install mcp-xpath for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @thirdstrandstudio/mcp-xpath --client claude
# Install dependencies
npm install

# Build the package
npm run build

Setup

Usage with Claude Desktop

Add the following to your claude_desktop_config.json:

npx

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

Direct Node.js

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

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

Examples

Query XML content

// Select all <item> elements from 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 from 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 from a webpage
const result = await callTool("xpathwithurl", {
  url: "https://example.com",
  query: "//a/@href",
  mimeType: "text/html"
});

Development

# Install dependencies
npm install

# Start the server in development mode
npm start

License

This MCP server is licensed 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, please see the LICENSE file in the project repository.

Instal\u00b7lem i gestionem el teu servidor MCP

El nostre equip configura, desplega i manté servidors MCP adaptats a la teva infraestructura.

  • Instal\u00b7lació i configuració professional
  • Integració amb els teus sistemes existents
  • Suport tècnic i manteniment continu
  • Seguretat i auditoria personalitzada

Resposta en menys de 24h · Sense compromís

Consulta ràpida sobre MCP

Relacionats a Extracció de dades web - MCP Servers segurs