How do I use mcp-homedepot?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-homedepot I need to find a cordless drill" 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-homedepot

by sstepanovvl

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

mcp-homedepot

License: PolyForm Noncommercial 1.0.0 Node

A Model Context Protocol server for Home Depot Canada (homedepot.ca). It exposes the store's product catalogue — search, product detail, store-level stock and a store finder — to MCP clients such as Claude and Cursor.

Unofficial. This project is not affiliated with, endorsed by, or sponsored by The Home Depot. It reads publicly available endpoints of homedepot.ca for personal, noncommercial use. Respect Home Depot's terms of service and use responsibly.

Tools

Tool	Description
`hd_search`	Product search / listings by keyword. Returns products (SKU, name, brand, model, price, rating, online stock, URL, image), total count, facets and sort options.
`hd_product`	Full product card by SKU: name, brand, model, description, images, rating/reviews, warranty, categories, price, in-store stock + aisle/bay, online stock, fulfillment options.
`hd_store_availability`	In-store stock of a SKU across a store and its nearby stores, sorted in-stock first. Per store: name, address, phone, coordinates, stock level/status, aisle/bay, pickup status.
`hd_stores`	Store directory / find stores near a postal code (geocoded → distance-sorted with `distanceKm`), or the full national directory (~183 stores).

More tools (suggestions, categories) are planned.

`hd_search`

Param	Type	Default	Notes
`query`	string	—	Search keyword (required).
`storeId`	string	`9999`	Store id for store-specific stock/pricing.
`lang`	`en` \| `fr`	`en`	Response language.
`sort`	`relevance` \| `price-asc` \| `price-desc` \| `reviewAvgRating`	`relevance`	Sort order.
`page`	int	`0`	0-indexed page.
`pageSize`	int (1–60)	`24`	Results per page.

`hd_product`

Param	Type	Default	Notes
`sku`	string	—	Product SKU / code (required), e.g. `1001686659`.
`postalCode`	string	—	Postal code, e.g. `M5V 2T6`; uses the nearest store (overrides `storeId`).
`storeId`	string	`7074`	Store id for store-specific price/stock/aisle. Override default with `HD_DEFAULT_STORE`.
`lang`	`en` \| `fr`	`en`	Response language.

`hd_store_availability`

Param	Type	Default	Notes
`sku`	string	—	Product SKU / code (required).
`postalCode`	string	—	Postal code; nearby stores are taken around it (overrides `storeId`).
`storeId`	string	`7074`	Reference store; nearby stores are taken from it.
`lang`	`en` \| `fr`	`en`	Response language.
`limit`	int (1–20)	`10`	Max number of stores to check.

Default store: product/availability tools default to store 7074 (Langford, BC). Set HD_DEFAULT_STORE env var, or pass storeId, to use your local store. Use hd_stores with a postal code to find the right store id.

`hd_stores`

Param	Type	Default	Notes
`postalCode`	string	—	Canadian postal code, e.g. `M5V 2T6`. Returns nearest stores with `distanceKm`.
`latitude` / `longitude`	number	—	Alternative to `postalCode` for proximity.
`lang`	`en` \| `fr`	`en`	Response language.
`limit`	int (1–200)	20 / all	Max stores. Default 20 for a proximity search, all (~183) otherwise.

The store API geosorts by coordinates only, so a postal code is first geocoded via api.zippopotam.us (free, no key). distanceKm is computed locally (haversine).

Related MCP server: MCP Tools

How it talks to Home Depot

homedepot.ca/api/* is behind Akamai Bot Manager, which gates on both the HTTP version and the client's TLS (JA3) fingerprint. Node's native HTTP stack (fetch/undici, node:http2) gets 403. Only curl --http2 is allowlisted, so every request shells out to curl. No cookies are needed for the public search APIs.

Requirement: curl with HTTP/2 support must be on PATH (standard on macOS and most Linux distros).

Build & run

npm install
npm run build
npm start          # runs the MCP server on stdio

Quick smoke test of the search layer:

node --input-type=module -e 'import {search} from "./dist/search.js"; console.log(await search({query:"drill", pageSize:3}))'

Inspect with the MCP Inspector:

npm run inspect

Connecting a client

Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json), pointing at the built entrypoint:

{
  "mcpServers": {
    "homedepot": {
      "command": "node",
      "args": ["/absolute/path/to/mcp_homedepot/dist/index.js"],
      "env": { "HD_DEFAULT_STORE": "7074" }
    }
  }
}

HD_DEFAULT_STORE is optional (defaults to 7074, Langford BC).

Project layout

src/
  index.ts    MCP server + tool registration (stdio)
  hd.ts       curl --http2 transport for homedepot.ca
  search.ts   hd_search implementation + response mapping
  product.ts  hd_product + hd_store_availability (summary, buybox, storesvc APIs)
  stores.ts   hd_stores (store directory + postal-code geocode → nearest)

License

PolyForm Noncommercial License 1.0.0 — free to use, modify and share for noncommercial purposes. Commercial use requires a separate license from the author.

Available Tools

4 tools

hd_productGet Home Depot Canada product by SKUA

Fetch the full product card for a Home Depot Canada SKU (product code): name, brand, model, description, images, rating/reviews, warranty, categories, price, in-store stock with aisle/bay location, online stock, and fulfillment options (pickup in store, ship to store, ship to home, express delivery) for a given store.

ParametersJSON Schema

Name	Required	Description
`sku`	Yes	Product SKU / code, e.g. '1001686659' (from hd_search results).
`postalCode`	No	Postal code, e.g. 'M5V 2T6'; uses the nearest store (overrides storeId).
`storeId`	No	Store id for store-specific price/stock/aisle. Default 7074.
`lang`	No	Response language. Default 'en'.

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description must convey behavior. It describes the output comprehensively but does not mention side effects (likely none), authorization needs, rate limits, or error scenarios. This is adequate for a read-only tool but lacks full transparency.

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 a single sentence that front-loads the primary action and then lists outputs concisely. It is efficient without unnecessary words. Slightly longer due to detail, but still well-structured.

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

Completeness3/5

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

Given 4 parameters and no output schema, the description covers the returned fields well and references a sibling tool (hd_search) for input. However, it lacks information on error handling (e.g., invalid SKU) or any prerequisites beyond the SKU. This is adequate but could be more complete.

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

Parameters4/5

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

Schema description coverage is 100%, so each parameter is already documented. The description adds value by providing usage context (e.g., SKU from hd_search, postal code overrides storeId, default storeId). This enhances comprehension beyond the schema alone.

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 clearly states the action ('Fetch'), the resource ('full product card for a Home Depot Canada SKU'), and details the returned fields. It distinguishes from sibling tools like hd_search (which is for searching) and hd_store_availability (likely for specific availability).

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

Usage Guidelines3/5

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

The description implies use after obtaining a SKU, especially via the sku parameter example 'from hd_search results'. However, it does not explicitly state when to use this tool vs alternatives, nor when not to use it. More explicit guidance would improve selection accuracy.

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

hd_searchSearch Home Depot CanadaA

Search Home Depot Canada (homedepot.ca) for products by keyword. Returns matching products with SKU, name, brand, model, price, rating, online stock, URL and image, plus the total result count, available filters (facets) and sort options. Use page to paginate.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Search keyword, e.g. 'cordless drill', 'paint roller'.
`storeId`	No	Store id for store-specific stock/pricing. Default 9999 (national).
`lang`	No	Response language. Default 'en'.
`sort`	No	Sort order. Default 'relevance'.
`page`	No	0-indexed page number. Default 0.
`pageSize`	No	Results per page (1-60). Default 24.

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses return fields (SKU, name, brand, etc.) and pagination behavior, but does not explicitly state that the operation is read-only or safe, nor does it mention error conditions, rate limits, or authentication needs. The implied read-only nature of 'search' is reasonable but not explicit.

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

Conciseness5/5

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

The description is two concise sentences. The first sentence states the purpose and lists return fields; the second provides a key usage hint. Every word contributes value with no redundancy.

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

Completeness4/5

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

Given the lack of an output schema, the description adequately lists return fields (SKU, name, brand, model, price, rating, online stock, URL, image) and mentions total count, filters, and sort options. It covers pagination with `page`. Missing details on error handling or defaults, but sufficient for a typical search tool.

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 covers all 6 parameters with descriptions (100% coverage), so the description adds minimal value beyond schema. It provides a pagination hint ('Use `page` to paginate'), which is mildly helpful but not essential. Baseline 3 is appropriate as schema carries the load.

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 clearly states it searches Home Depot Canada for products by keyword, providing a specific verb and resource. It lists the return fields (SKU, name, brand, etc.), distinguishing it from sibling tools like hd_product (single product details) and hd_stores (store info).

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 specifies when to use the tool: to search for products by keyword. It mentions pagination with `page`, implying its use for browsing. However, it does not explicitly state when not to use it or provide alternatives among siblings, though the sibling names are distinct enough to infer.

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

hd_store_availabilityCheck Home Depot Canada store availability for a SKUA

Check in-store stock of a Home Depot Canada SKU across a store and its nearby stores. Returns, per store: store name, address, phone, coordinates, stock level/status, aisle/bay location, and pickup status. Sorted with in-stock stores first. Use to answer 'which store has this in stock near me'.

ParametersJSON Schema

Name	Required	Description
`sku`	Yes	Product SKU / code, e.g. '1001686659'.
`postalCode`	No	Postal code, e.g. 'M5V 2T6'; nearby stores are taken around it (overrides storeId).
`storeId`	No	Reference store; nearby stores are taken from it. Default 7074.
`lang`	No	Response language. Default 'en'.
`limit`	No	Max number of stores to check (1-20). Default 10.

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return values (store name, address, phone, coordinates, stock level/status, aisle/bay, pickup status) and sorting (in-stock first). It also notes that nearby stores are derived from postalCode or storeId, with override logic. No destructive actions are implied, and the read-only nature is clear.

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

Conciseness5/5

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

The description is two sentences: the first defines the tool's action and output, the second provides a use case. It is front-loaded with essential information, contains no filler, and is optimally concise.

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

Completeness4/5

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

Given the tool's moderate complexity (5 parameters, 1 required, no output schema), the description adequately covers return fields, sorting, and parameter interactions. It does not mention error handling or edge cases, but it is sufficient for typical use.

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

Parameters4/5

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

The schema has 100% coverage, so the baseline is 3. The description adds value by stating the default for storeId (7074) and explaining that postalCode overrides storeId, which is not in the schema. This extra context helps the agent understand parameter relationships.

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 clearly states the tool checks in-store stock for a SKU across a store and nearby stores, returning detailed per-store information. It uses a specific verb ('check') and resource ('in-store stock of a Home Depot Canada SKU'), and the purpose is distinct from siblings (hd_product, hd_search, hd_stores).

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 explicitly advises using the tool to answer 'which store has this in stock near me', which gives clear context. It doesn't explicitly state when not to use it or list alternatives, but the sibling tool names imply those boundaries.

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

hd_storesHome Depot Canada store directory / find stores by postal codeA

List Home Depot Canada stores. With postalCode, returns stores nearest to it first (use to find a store id for hd_product / hd_store_availability). Without postalCode, returns the full national store directory (all ~183 stores). Each store: id, name, address, town, province, postal code, phone, coordinates, URL, and fulfillment eligibility (pickup in store / ship to store / ship from store).

ParametersJSON Schema

Name	Required	Description
`postalCode`	No	Canadian postal code, e.g. 'M5V 2T6'. Returns nearest stores with distanceKm. Omit to list all stores.
`latitude`	No	Latitude (alternative to postalCode for proximity).
`longitude`	No	Longitude (used with latitude).
`lang`	No	Response language. Default 'en'.
`limit`	No	Max stores to return. Default 20 for a proximity search, all stores otherwise.

TDQS

A4.4/5.0

Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses that the tool returns store details including IDs, addresses, and fulfillment eligibility, implying a read-only operation. It does not mention rate limits, authentication, or side effects, but the behavior is transparent enough for a listing tool.

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

Conciseness5/5

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

The description is exactly two sentences, front-loading the core purpose and then expanding on variations and output. Every word adds value, with no redundancy.

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

Completeness4/5

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

Given no output schema, the description enumerates return fields (id, name, address, etc.) and mentions behavior for proximity search. It lacks details on pagination or error responses, but for a straightforward list tool, it is sufficiently complete.

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

Parameters4/5

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

Schema coverage is 100%, providing baseline 3. The description adds value by clarifying that postalCode returns nearest stores with distanceKm, and that limit defaults differ per mode. This goes beyond schema descriptions, justifying a 4.

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 explicitly states it lists Home Depot Canada stores, with two modes (with/without postalCode), and directly relates to finding store IDs for sibling tools hd_product and hd_store_availability, distinguishing its purpose.

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 explains when to use postalCode (nearest stores) and when to omit (full directory), and mentions its utility for other tools. However, it does not explicitly contrast with sibling tools like hd_search or hd_store_availability, leaving some ambiguity for an agent.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv0.1.0Jun 23, 2026
- First observedhd_product
- First observedhd_search
- First observedhd_store_availability
- First observedhd_stores

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored 2026-06-23 07:20 across 4 tools

Disambiguation5/5

Each tool has a distinct, non-overlapping purpose: product details, search, store availability, and store directory. No confusion between them.

Naming Consistency5/5

All tools follow the consistent pattern 'hd_<noun>', with clear and predictable names that describe their function.

Tool Count5/5

Four tools is well-scoped for a retail product information and store location service. Each tool is necessary and sufficient for typical queries.

Completeness5/5

The tool set covers core operations: search, product details, store list, and availability per store. No obvious gaps for the intended use case.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Mercado PagoOAuth
com.mercadopago.mcp
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Finance E-commerce & Retail App Automation
2
DataDoe MCPOAuth
com.datadoe
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
E-commerce & Retail CRM
214
hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
238
mcp COAuth
com.wix
A Model Context Protocol server for Wix AI tools
Developer Tools Content Management Systems App Automation
216

Related MCP Servers

BigGo MCP Server
E-commerce & Retail Search Data Platforms
Funmula-Corp
A
license
C
quality
C
maintenance
A Model Context Protocol server enabling product searches across e-commerce platforms, price history tracking, and product specification-based searches using natural language prompts.
Updated a year ago (2025-04-30 09:35 UTC)
2
19
MIT
MCP Tools
Shell Access File Systems
ZbigniewTomanek
A
license
Not graded
quality
D
maintenance
A custom Model Context Protocol server that gives Claude Desktop and other LLMs access to file system operations and command execution capabilities through standardized tool interfaces.
Updated a year ago (2025-04-16 09:10 UTC)
23
Apache 2.0
FireBall1725/pcexpress-mcp
E-commerce & Retail Search
FireBall1725
A
license
Not graded
quality
A
maintenance
Control your grocery cart with AI! This MCP server enables LLMs (like Claude) to search past orders, find products, and manage your shopping cart across all Loblaws-owned grocery banners.
Updated 24 days ago (2026-08-21 23:23 UTC)
8
AGPL 3.0
Mouser Electronics MCP Server
E-commerce & Retail Search
nickweedon
A
license
A
quality
F
maintenance
A Model Context Protocol (MCP) server for the Mouser Electronics API. Enables searching electronic components, managing shopping carts, and tracking orders directly through Claude or other MCP clients.
Updated 9 months ago (2025-12-25 20:02 UTC)
9
5
MIT