npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@trustrails/mcp-server

v1.0.23

Published

MCP server for searching UK electronics products across multiple retailers

Readme

TrustRails MCP Server

Search UK electronics products - compare prices, find deals, and discover products across multiple retailers.

Built for the Model Context Protocol (MCP) - works with Claude Desktop, Claude Code, and other MCP-compatible AI assistants.

npm version License: MIT


Quick Start

No installation needed — just add TrustRails to your Claude config.

Configuration

For Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "trustrails": {
      "command": "npx",
      "args": ["-y", "@trustrails/mcp-server"],
      "env": {
        "TRUSTRAILS_API_KEY": "mcp-public-2026"
      }
    }
  }
}

For Claude Code (~/.config/claude/config.json):

{
  "mcpServers": {
    "trustrails": {
      "command": "npx",
      "args": ["-y", "@trustrails/mcp-server"],
      "env": {
        "TRUSTRAILS_API_KEY": "mcp-public-2026"
      }
    }
  }
}

That's it! Restart Claude and start searching.


What You Can Do

Natural Language Product Search

Just ask Claude naturally — it will decompose your request into the right query and filters:

"Find me a gaming laptop under £1000"
"I need Sony noise cancelling headphones"
"What HP laptops are available between £500-£700?"
"Show me Anker chargers"

Claude will search across multiple UK retailers and show you:

  • Real-time prices & availability
  • Direct purchase links
  • Then call get_product for full specs when you need details

Available Tools

search_products

Search 26,000+ UK electronics products. Returns summary data (title, price, availability, category). For full technical specs, use get_product.

Parameters:

  • query (string) - Refinement terms after brand and category are extracted: model lines, series, variants, technology descriptors, or model numbers (e.g., "neo", "ultra", "oled", "WH-1000XM5"). Omit entirely if brand + category alone describe what's needed. Never put brand names, product family names, or prices here — use filters.
  • min_price (number, optional) - Minimum price in GBP
  • max_price (number, optional) - Maximum price in GBP
  • brand (string, optional) - Filter by brand, exact match (e.g., "Sony", "HP", "Apple")
  • category (string, optional) - Filter by category: Laptops, Desktops, Tablets, Phones, TVs, Monitors, Headphones, Speakers, Cameras, Keyboards, Mice, Printers, Networking, Storage, Gaming, Wearables, Drones, Audio, Cables & Chargers.
  • lite (boolean, optional) - Return trimmed product objects (reduces payload by ~80%). Always use for LLM integrations.
  • limit (number, optional) - Maximum products to return (default 50, max 100)
  • sort (string, optional) - Sort order: relevance (default), price_asc (cheapest first), price_desc (most expensive first). Use price_asc when comparing prices.

Returns: Up to 50 products with summary data. With lite: true, returns only essential fields (id, title, brand, price, availability, image_url, purchase_url).

get_product

Get full details for a single product. Returns complete technical specifications including specs.description (full prose spec text with processor, RAM, storage, display, ports, etc.), stock level, delivery time, and all retailer offers with per-retailer pricing. Use after search_products for detailed comparison or recommendations.

Parameters:

  • product_id (string) - The product ID from search results

Returns: Complete product with full specs (including specs.description), pricing across all retailers, and provenance information


Supported Retailers

Search across 26,000+ electronics products from major UK retailers including AO, with new retailers added regularly.


Example Usage

Budget shopping:

"Find gaming laptops under £800"
→ category='Laptops', query='gaming', max_price=800, sort='price_asc', lite=true

Brand search:

"I need Sony headphones under £200"
→ brand='Sony', category='Headphones', max_price=200, sort='price_asc', lite=true

Category browsing:

"Show me cheap monitors"
→ category='Monitors', max_price=200, lite=true

Detailed specs:

"Tell me the full specs of this laptop"
→ get_product(product_id) — returns full technical specifications

Price range:

"Apple products between £500 and £1000"
→ brand='Apple', min_price=500, max_price=1000, lite=true

Rate Limits

  • 50 requests per hour per IP address
  • Rate limit info included in response headers
  • Limits reset every hour

Environment Variables

  • TRUSTRAILS_API_KEY - API key (use mcp-public-2026 for shared public access)
  • TRUSTRAILS_BASE_URL - API endpoint (optional, defaults to https://trustrails.app)

Why TrustRails?

  • Real-time data - Product feeds updated twice daily
  • Multiple retailers - Compare prices in one search
  • Stock information - See what's actually available to buy
  • Direct purchase links - Click through to buy immediately
  • Zero setup - Works out of the box with shared public key
  • UK-focused - Optimized for UK electronics shopping

Troubleshooting

"Command not found" or server not starting

  • Make sure Node.js is installed and npx is available: npx --version
  • Try running manually: npx -y @trustrails/mcp-server
  • Using nvm? Claude Desktop doesn't inherit your shell PATH. Use the full path to node instead:
    {
      "command": "/Users/YOUR_USERNAME/.nvm/versions/node/vX.X.X/bin/node",
      "args": ["/Users/YOUR_USERNAME/.nvm/versions/node/vX.X.X/lib/node_modules/@trustrails/mcp-server/dist/index.js"]
    }
    First run npm install -g @trustrails/mcp-server, then find your node path with which node.

"Rate limit exceeded"

  • Wait an hour for limits to reset
  • Check X-RateLimit-Reset header for exact reset time
  • 50 requests/hour is plenty for normal usage

"No results found"

  • Try broader search terms (e.g., "laptop" instead of specific model)
  • Check spelling of brand names
  • Try searching without filters first

Development

Local Setup

# Clone the repo
git clone https://github.com/james-webdev/trustrails-mcp-server
cd trustrails-mcp-server

# Install dependencies
npm install

# Run locally
npm run dev

Testing

# Run the MCP inspector to test tools
npx @modelcontextprotocol/inspector npm run dev

Support & Links


License

MIT © TrustRails


About MCP

This server implements the Model Context Protocol, a standard for connecting AI assistants to external tools and data sources. Learn more about building MCP servers at modelcontextprotocol.io.