Package Exports

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@trustrails/mcp-server) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

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.

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

Website: trustrails.app
Issues: GitHub Issues
NPM: @trustrails/mcp-server
MCP Registry: modelcontextprotocol.io/servers

License

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.