Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-walmart search for organic milk under $5"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server connector for Walmart retail shopping — search products, manage cart, and track orders via browser automation.
This connector enables autonomous shopping on behalf of your human. Agents can:
Know what to buy: Understand shopping lists, dietary preferences, budget constraints, and seasonal needs
Search intelligently: Find products with filters (price, ratings) and compare options
Execute efficiently: Build a cart, review totals, and hand off for final purchase confirmation
Track orders: Monitor delivery status and notify the user when items arrive
Example agent workflow:
User: "I need groceries for the week. My budget is $100, and I need vegetarian options."
Agent executes:
set_address → Get local store availability
search → "organic vegetables", max_price: 50
search → "rice, pasta, beans" with filters
get_product → Check nutrition and price for each
add_to_cart → Build optimized cart under $100
checkout → Review total ($94.32) and return summary to user
User approves → Agent completes purchase
All in one seamless agent turn.
Related MCP server: @retailerapi/mcp
This package provides a Model Context Protocol (MCP) server that enables AI agents to interact with Walmart.com through Playwright browser automation with stealth features to avoid bot detection.
npx @striderlabs/mcp-walmartOr install globally:
npm install -g @striderlabs/mcp-walmart
mcp-walmartAdd to your MCP client configuration:
{
"mcpServers": {
"walmart": {
"command": "npx",
"args": ["@striderlabs/mcp-walmart"]
}
}
}statusCheck Walmart authentication status and session info.
No parameters required.
{}loginAuthenticate with your Walmart account using email and password via browser automation.
Parameter | Type | Required | Description |
| string | Yes | Walmart account email |
| string | Yes | Walmart account password |
| boolean | No | Run browser headless (default: |
logoutClear Walmart session and stored cookies.
No parameters required.
set_addressSet delivery or pickup address for Walmart. Affects product availability and pricing.
Parameter | Type | Required | Description |
| string | No* | ZIP code (e.g., |
| string | No* | Full address (e.g., |
*At least one of zip_code or address is required.
searchSearch Walmart products by query with optional filters.
Parameter | Type | Required | Description |
| string | Yes | Search term |
| number | No | Minimum price filter |
| number | No | Maximum price filter |
| string | No | Sort order: |
| number | No | Max results (default: |
get_productGet detailed product information including price, description, and availability.
Parameter | Type | Required | Description |
| string | No* | Full Walmart product URL |
| string | No* | Walmart product item ID |
*At least one of url or item_id is required.
add_to_cartAdd a product to the Walmart cart.
Parameter | Type | Required | Description |
| string | No* | Walmart product URL |
| string | No* | Walmart product item ID |
| number | No | Quantity to add (default: |
*At least one of url or item_id is required.
view_cartView current Walmart cart contents and totals.
No parameters required.
update_cartUpdate the quantity of an item in the Walmart cart.
Parameter | Type | Required | Description |
| number | Yes | New quantity (must be >= 1) |
| string | No* | Walmart product item ID |
| string | No* | Partial product name to match |
*At least one of item_id or product_name is required.
remove_from_cartRemove a specific item from the Walmart cart.
Parameter | Type | Required | Description |
| string | No* | Walmart product item ID |
| string | No* | Partial product name to match |
*At least one of item_id or product_name is required.
checkoutPreview checkout summary for the Walmart cart. Returns order details without placing the order.
No parameters required.
Note: This tool intentionally does not place the order. It returns the order summary (items, subtotal, tax, total) so you can review before proceeding manually.
get_ordersGet Walmart order history.
Parameter | Type | Required | Description |
| number | No | Number of recent orders to return (default: |
Cookies and auth info are stored in ~/.striderlabs/walmart/ and persist across sessions. Once logged in, subsequent tool calls reuse the existing session without re-authenticating.
Transport: stdio (standard MCP transport)
Browser: Chromium via Playwright with stealth patches
Bot detection bypass: Removes webdriver flag, spoofs plugins/languages, patches permissions API
Session storage: ~/.striderlabs/walmart/cookies.json and ~/.striderlabs/walmart/auth.json
Node.js >= 18.0.0
Chromium (installed automatically with Playwright)
MIT — Strider Labs
Search Walmart products by query with optional filters
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results (default: 10, max: 24) | |
| query | Yes | Search term | |
| sort_by | No | Sort order | |
| max_price | No | Maximum price filter | |
| min_price | No | Minimum price filter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden but only mentions 'search with optional filters', lacking details on pagination, rate limits, or data behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very short (6 words), efficient and front-loaded, but could include slightly more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite 5 parameters and no output schema, description lacks details on return format, pagination (limit mentioned in schema only), or any behavioral context beyond generic search.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters (100% coverage), so baseline is 3; description adds only 'optional filters' which adds minimal value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Search Walmart products by query with optional filters', specifying verb, resource, and scope. Distinguishes from sibling 'update_cart'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs. alternatives, no when-not-to-use instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the quantity of an item in the Walmart cart
| Name | Required | Description | Default |
|---|---|---|---|
| item_id | No | Walmart product item ID to update | |
| quantity | Yes | New quantity (must be >= 1) | |
| product_name | No | Partial product name to identify item (alternative to item_id) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully relies on itself. It does not disclose critical behaviors such as whether the update is incremental, whether it fails if item not in cart, or required authentication or session state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence with no extraneous words. It efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters and no output schema or annotations, the description is too brief. It omits important details like return format, error handling, or conditions (e.g., item must be in cart). The context is insufficient for an AI agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters. The description does not add meaningful additional semantics beyond the schema; it repeats 'quantity' but no extra context. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update the quantity') and the resource ('an item in the Walmart cart'), distinguishing it from the sibling tool 'search' which is for searching products.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., adding items, removing items), nor prerequisites like item existence in cart. The description gives no context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0searchupdate_cartThe two tools have completely distinct purposes: one for searching products, the other for updating cart quantities. No overlap.
Both tools follow a consistent verb_noun snake_case pattern (search, update_cart), making them predictable.
With only 2 tools, the set feels too thin for a Walmart shopping server. Typical shopping tasks like add to cart, get cart, or remove item are missing.
There are obvious gaps: no add_to_cart, get_cart, remove_from_cart, or any order management. The surface only covers search and cart update, leaving essential operations absent.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/markswendsen-code/mcp-walmart'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
