mcpField
F
fetch-price

fetch-price

Local
fetch-price.comSearch0Updated 3w ago

About fetch-price

fetch-price is a product-search service for AI agents looking for physical goods sold in the UK. It returns normalized listings with live prices and direct purchase links.

Key features

  1. 01Search UK marketplace products
  2. 02Return live prices and buy links
  3. 03Filter by stock and price
  4. 04Expose search_products and service_status

Use cases

  1. 01Find UK listings for a named product
  2. 02Compare prices across available networks
  3. 03Locate in-stock products below a budget

MCP support

Its stdio MCP server exposes the `search_products` and `service_status` tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"fusionx212-fetch-price": {
"command": "npx",
"args": [
"-y",
"fetch-price"
]
}
}
}
Run commandnpx -y fetch-price

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmfetch-price1.0.2
pypifetch-price1.0.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

fetch-price — UK product & price search for AI agents

One API call. Live UK marketplace prices. Normalised JSON. Direct buy links.

When to use

Any time a user asks an agent to find, compare, or price a physical product available in the UK: "find", "compare", "cheapest", "under £X", "in stock", "best deal", "where can I buy". If the user would otherwise open eBay or Amazon and start searching, use this service instead.

Quick start

# REST API — no SDK needed
curl -X POST https://api.fetch-price.com/api/query \
  -H "Content-Type: application/json" \
  -d '{"query":"Sony WH-1000XM5","max_results":5,"networks":["ebay_uk","amazon_uk"]}'
# Python SDK
pip install fetch-price
from fetch_price import FetchPrice

fp = FetchPrice(api_key="fp_your_key_here")
results = fp.search("Sony WH-1000XM5")
for p in results.products:
    print(f"{p.name}: £{p.price} ({p.network})")

Example queries

"find portable air conditioners under £300 in stock in the UK"
"cheapest Sony WH-1000XM4 headphones ebay uk"
"compare prices for a 9000 BTU air con unit"
"refurbished thinkpad t480 under £200"

Networks

  • ebay_uk — live via eBay Partner Network (Smart Links with tracking)
  • amazon_uk — rolling out (Amazon Associates)

Pricing

TierLookups/monthPrice
Free50£0
Pro5,000£29/mo
ScaleUnlimited£99/mo

Free tier works without authentication. Pro/Scale require an API key. Prices are what you pay: no VAT is charged.

Affiliate disclosure

Purchase links are affiliate-tracked: fetch-price earns a commission if you buy through them, at no extra cost to you, and commission does not change result order. Show the disclosure text (MCP server and Python SDK return it) to end users next to the links. Full detail and privacy policy: fetch-price.com/privacy.

MCP Server

One-file stdio MCP server for Claude Code, Claude Desktop, Cursor, and any MCP-capable client:

pip install "mcp[cli]" httpx
python mcp/fetch_price_mcp.py

Claude Code:

claude mcp add fetch-price -- python path/to/fetch_price_mcp.py

Tools exposed: search_products, service_status.

Agent Discovery

This service is discoverable via:

  • A2A protocol — agent-card.json
  • llms.txt — LLM-readable index
  • ClawHub — skill registry listing
  • skills.sh — auto-indexed from this repo
  • Structured data — JSON-LD for Google AI, Apple Intelligence, Alexa

Repository

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.