Skip to main content
Glama
HasData

Walmart MCP Server

walmart_reviews: GET /

hasdata_walmart_reviews_getWalmartReviews

Scrape Walmart product reviews by item ID or URL for review mining and sentiment analysis. Filter by star rating, verified purchases, or condition and sort by relevance or recency.

Instructions

Get Walmart Product Reviews

Scrapes the customer reviews of one Walmart product on a chosen storefront by item id or URL, ten reviews a page. Returns each review with its rating, title, full text with paragraphs preserved, submission date, author, verified-purchase flag, helpful and not-helpful vote counts, badges, marketplace seller, photos and videos, and the review aspects it was tagged with. Alongside the reviews it returns the item rating, how many ratings versus how many written reviews exist, the per-star breakdown, the AI review summary, per-aspect scores such as Quality or Value for money, and a filters block listing exactly which star ratings, frequent mentions and conditions this item can be filtered by, with a count for each - the values in that block are the ones to pass back as request parameters. Sort by most relevant, most recent, most helpful, highest rated, lowest rated or oldest, and filter by star rating, frequent mention, condition or verified purchases only. Use for review mining and sentiment analysis, tracking what buyers praise or complain about per product, monitoring new reviews over time, and pulling only verified-purchase feedback.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoA full Walmart product URL whose reviews to scrape. When provided, it overrides `itemId` and the storefront is taken from the URL itself. Required unless `itemId` is provided.
pageNoPage of reviews to return, ten reviews a page. The response reports the last available page in `pagination.totalPages`, the next one in `pagination.nextPage`, and how many reviews the current filters select in `pagination.totalResults`. Note that only reviews carrying written text are paginated, so the ceiling follows `reviewsInformation.totalReviews` rather than the larger `reviewsInformation.totalRatings`. Default is `1`.
sortNoOrder of the returned reviews, named as the Walmart review page names it. Default is `mostRelevant`.
domainNoWalmart storefront the item belongs to. Each storefront has its own catalog, item ids and review pool, so an id from one storefront does not resolve on another. Ignored when `url` is provided. Default is `walmart.com`.
itemIdNoWalmart item id, taken from a product URL or from the id field of the Walmart Search API response. On `walmart.com` it is numeric (for example `14977205582`), on `walmart.ca` an alphanumeric code (for example `6NZMJ5CW6MH2`). Required unless `url` is provided.
ratingNoReturn only reviews carrying this star rating, from `1` to `5`. The Star rating group of the `filters` block lists the ratings this item actually has, each with the `value` to send here and a `count` of how many reviews to expect.
aspectIdNoReturn only reviews mentioning one topic. Send the `value` of the topic you want, taken from the Frequent mentions group of the `filters` block in the response - given `{"name": "Battery Life", "value": "6049", "count": 8}` you send `6049`, and `count` is how many reviews to expect. **Only one topic per request**, Walmart rejects a list of them. Topics belong to the product rather than to Walmart: a phone offers Battery Life or Display, a coffee offers Flavor or Aroma, and some items offer none at all - so make an unfiltered request first and read the block, instead of reusing a topic id across products.
languageNoLanguage of the review page. Availability depends on the storefront - `walmart.com` serves `en` and `es`, `walmart.ca` serves `en` and `fr`. A language the storefront does not support falls back to its default. Reviews themselves are returned in the language their author wrote them in.
conditionNoReturn only reviews written about one condition of the item. Send the `value` from the Condition group of the `filters` block - given `{"name": "Restored: Like New", "value": "5"}` you send `5`. **Only one condition per request.** This group appears for items Walmart sells in several conditions, and only when the request already names one: reach the variant through the `url` parameter with its `conditionGroupCode`, as in `https://www.walmart.com/ip/1028936148?conditionGroupCode=2`, and the block then lists the condition that variant carries. An item sold in a single condition has no such group, and no reviews to separate by it.
verifiedPurchasesOnlyNoReturn only reviews left by customers whose purchase Walmart confirmed. Narrows the pool considerably, since most reviews are unverified or syndicated from the manufacturer.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it does so thoroughly. It discloses the ten-reviews-per-page behavior, pagination limits tied to written reviews, the need to pass filter-block values back as request parameters, single-topic and single-condition limits, language/storefront fallback behavior, and the narrowing effect of verifiedPurchasesOnly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with its purpose and then packs substantial response and filtering detail into the following sentences. It is long, but nearly every clause contributes useful information; the use-case sentence is somewhat discretionary, and a few overly long sentences could be split without losing content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description appropriately explains what the response contains: review fields, item rating, rating-versus-review counts, per-star breakdown, AI summary, aspect scores, and the filters block. Combined with the schema's detailed parameter documentation, an agent has enough context to invoke the tool and interpret its results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents all 10 parameters at 100% coverage, including concrete examples, enums, defaults, and filter-value mappings. The tool description mostly summarizes these capabilities at a high level rather than adding new parameter-level meaning, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Get Walmart Product Reviews' and immediately specifies the action: scraping the customer reviews of one Walmart product by item id or URL. It also enumerates the extracted review data and aggregate info, making it clearly distinguishable from the sibling product and search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit use cases such as 'review mining and sentiment analysis', 'tracking what buyers praise or complain about per product', 'monitoring new reviews over time', and 'pulling only verified-purchase feedback'. It does not explicitly name the sibling tools or state when not to use this one, but the review-focused scope makes the intended context clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HasData/walmart-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server