Sign inTry it

Walmart MCP server: let your AI agent search products with price and availability

Wield is an MCP server that gives your AI agent one Walmart tool. It searches Walmart.com like the site's own search and returns the product name, current and previous price in US dollars, rating, seller, availability and badges. The search runs in your own browser with your own session and needs no login. In our benchmark the recipe passed 9 of 9 runs.

Updated

Live recipewalmart.com/search-productsv1

Walmart Search Walmart products with price, rating and availability

Read-only, no loginRuns in your browser only

Parameters (6)
include_sponsoredboolean
max_priceintegerUSD
min_priceinteger
pageinteger
querystringrequiredWhat to search for, e.g. 'air fryer'
sortstring "best_match" | "price_low" | "price_high" | "best_seller" | "rating_high"
Use it with your agent
Measured on the live site
MetricWield recipeBrowser Use + Claude Sonnet 5.5
Success100%0%
Median time2.1 s85 s
Cost per run$0$0.122

9 runs each, 7 November 2026. How we measure

What your agent gets

RecipeWhat it doesLoginStatus (7 Nov 2026)
walmart.com/search-productsSearches products: name, price, previous price, rating and reviews, seller, availability, badges such as Best seller or Rollback, image and linkNoOK

The parameters are query (required), sort (best match, price low to high, price high to low, best seller or rating high), min_price and max_price in dollars, page, and an option to include sponsored products. Sponsored products are dropped by default. Each product also comes with its image, seller and link. Availability and badges come from the listing itself. The how-to page has example prompts.

How a request flows

  1. You ask your agent: "Find a 65-inch TV under 500 dollars on Walmart, sorted by rating."
  2. The agent calls find_recipe, then run with walmart.com/search-products, your query, max_price: 500 and sort: rating_high.
  3. wield-mcp passes the run through a local bridge to the Wield extension.
  4. The extension sends the request from a walmart.com tab, so it carries your browser session.
  5. The results go back to your agent. Nothing passes through wield.run.

What leaves your computer

A search makes one request to www.walmart.com. Passwords and cookies never leave your computer. Wield logs the request on your computer only, without the body or query values. Buying stays on walmart.com.

Walmart terms, in plain words

Walmart's terms prohibit automated access and scraping. The recipe runs one user-started search page at a time, from your own browser. Buying stays on walmart.com. We have not completed a review of the terms for this recipe, so read them before you automate anything else.

Limits and what is not working yet

  • Bot protection. Walmart's bot protection blocked a server-side check in our tests, so we verified the recipe in the browser. Wield does not solve bot checks. When a check appears, Wield stops and asks you to solve it in your own tab.
  • Sponsored products are hidden by default. They appear only when you set include_sponsored.
  • One page per call. Use page to read the next set of results.
  • US dollars. Prices come back in US dollars.

FAQ

Is there an official Walmart MCP server?

Not that we know of as of 7 November 2026. Wield provides this search as a recipe that runs in your browser.

Which AI apps work with it?

Any MCP client. npx -y wield-mcp init sets up Claude Desktop, Claude Code, Cursor and Codex. The AI apps page lists each one.

Does it need a login?

No. The search runs without an account.

How fast is it compared with a browser agent?

In our benchmark, as of 7 Nov 2026 (preliminary, still running), the recipe passed 9 of 9 runs with a median of 2.1 seconds. Browser Use driving Claude Sonnet 5.5 passed 0 of 9 runs, with a median of 84.5 seconds and about $0.12 per run. Bot protection blocked the browser agent in all nine runs. The benchmark page has the method and raw logs.