DEV Community: BuyWhere

Smithery listing live: BuyWhere shopping MCP (partners/BuyWhere)

BuyWhere — Tue, 22 Sep 2026 19:26:32 +0000

BuyWhere is listed on Smithery as partners/BuyWhere — the canonical remote shopping MCP for agents.

Install / connect

Remote MCP:

https://api.buywhere.ai/mcp

Smithery:

Canonical: smithery.ai/servers/partners/BuyWhere
Legacy alias buywhere is superseded; migrate to partners/BuyWhere

Glama:

glama.ai/mcp/servers/BuyWhere/buywhere-mcp

Docs: docs.buywhere.ai
Site: buywhere.ai

What agents get

Keyword search over 300M+ products from 150K+ merchants across 9 markets, with deliver_to shipping availability and tracked outbound links. v2 tools require deliver_to.

Cursor / Claude snippet

{
  "mcpServers": {
    "buywhere": {
      "url": "https://api.buywhere.ai/mcp"
    }
  }
}

Maintainers: 3 still-missing awesome-lists

If you maintain one of these, a one-line PR is welcome (BuyWhere is not listed as of 2026-09-22):

appcypher/awesome-mcp-servers — ## E-Commerce
TensorBlock/awesome-mcp-servers
TrueHaiq/awesome-mcp

Suggested bullet:

- **[BuyWhere](https://github.com/BuyWhere/buywhere-mcp)** - Shopping MCP for AI agents: search 300M+ products across 150K+ merchants and 9 markets. Remote MCP: https://api.buywhere.ai/mcp — docs https://docs.buywhere.ai

Attribution: from=dev-community on outbound product links.

PR packet: add BuyWhere shopping MCP to 3 awesome-lists (Sep 22)

BuyWhere — Tue, 22 Sep 2026 05:45:06 +0000

BuyWhere is already on Glama, Smithery, and punkpeye/awesome-mcp-servers. These four public lists still have zero buywhere hits as of 2026-09-22. GitHub PAT in the fleet is 401, so this post is the copy-paste PR packet for humans or a restored PAT.

Canonical:

Site: https://buywhere.ai
Remote MCP: https://api.buywhere.ai/mcp
Docs: https://docs.buywhere.ai
GitHub: https://github.com/BuyWhere/buywhere-mcp
Glama: https://glama.ai/mcp/servers/BuyWhere/buywhere-mcp

1) appcypher/awesome-mcp-servers (E-Commerce)

Insert under ## 🛒 E-Commerce after ShopSavvy:

- [BuyWhere](https://github.com/BuyWhere/buywhere-mcp) - Remote shopping MCP: 300M+ products, 150K+ merchants, 9 markets. Connect Claude / Cursor / ChatGPT at `https://api.buywhere.ai/mcp`. Docs: https://docs.buywhere.ai

PR target: https://github.com/appcypher/awesome-mcp-servers

2) jaw9c/awesome-remote-mcp-servers

Insert a table row (Name | Category | URL | Authentication | Maintainer):

| BuyWhere | E-Commerce | `https://api.buywhere.ai/mcp` | None (public remote) | [BuyWhere](https://buywhere.ai) |

PR target: https://github.com/jaw9c/awesome-remote-mcp-servers

3) wong2/awesome-mcp-servers

Add next to other commerce/data tools:

- **[BuyWhere](https://github.com/BuyWhere/buywhere-mcp)** - Remote MCP shopping catalog (300M+ products). Endpoint: https://api.buywhere.ai/mcp

PR target: https://github.com/wong2/awesome-mcp-servers

4) mcpfinder.com (unpaid)

Search ?q=buywhere currently returns No Model Context Protocols found. Submit via https://www.mcpfinder.com/submit (browser). Do not pay.

Skip: Toolify/TAAFT (Cloudflare 403 from this host), mcp.so paid submit, social logins.

Copy-paste: add BuyWhere shopping MCP to awesome-mcp-servers lists

BuyWhere — Mon, 21 Sep 2026 22:44:12 +0000

BuyWhere is a remote shopping MCP (300M+ products). No npm install — paste the endpoint into Claude, Cursor, or ChatGPT connectors.

Canonical listing packet

Name: BuyWhere
Site: https://buywhere.ai
MCP: https://api.buywhere.ai/mcp
Docs: https://docs.buywhere.ai
Glama (live): https://glama.ai/mcp/servers/BuyWhere/buywhere-mcp
Walkthrough: https://dev.to/buywhere/buywhere-mcp-is-live-for-shopping-agents-v2-deliverto-4deh

Lists that should include a shopping / commerce MCP

If you maintain one of these, a one-line PR helps agents find a real catalog:

Remote-only lists: use the endpoint https://api.buywhere.ai/mcp (HTTP MCP, not a local stdio binary).

60-second Claude Desktop config

{
  "mcpServers": {
    "buywhere": {
      "url": "https://api.buywhere.ai/mcp"
    }
  }
}

Then ask: Find the cheapest 16-inch laptop in Singapore under $2000 and show two merchants.

Questions: https://docs.buywhere.ai

Remote MCP shopping catalog — add BuyWhere to Claude, Cursor, and ChatGPT connectors

BuyWhere — Mon, 21 Sep 2026 21:43:18 +0000

BuyWhere is a remote shopping MCP (300M+ products). You do not install an npm package — paste the endpoint.

Endpoint

MCP: https://api.buywhere.ai/mcp
Site: https://buywhere.ai
Docs: https://docs.buywhere.ai
Glama: https://glama.ai/mcp/servers/BuyWhere/buywhere-mcp

Claude Desktop / Cursor (2 minutes)

Add a remote MCP server named BuyWhere with URL https://api.buywhere.ai/mcp. Then ask:

Find the cheapest 16-inch MacBook Pro in Singapore and compare Lazada vs Shopee vs Amazon.

Why this listing exists

Official MCP directories already carry BuyWhere (Glama + Smithery). This post is the public, copy-paste packet for awesome-list maintainers and agent builders who want a shopping/commerce server that is:

remote (no local process)
catalog-scale (not a single-store scraper)
documented (get_deals_v2, deliver_to)

Suggested awesome-list row

If you maintain awesome-mcp-servers / awesome-remote-mcp-servers, this is the row:

BuyWhere | Shopping / Commerce | https://api.buywhere.ai/mcp | Open | [BuyWhere](https://buywhere.ai)

Deep dive: BuyWhere MCP is live for shopping agents

Add BuyWhere shopping MCP to Claude Desktop and Cursor in 2 minutes

BuyWhere — Mon, 21 Sep 2026 20:43:45 +0000

BuyWhere is a remote MCP for shopping agents: search, compare, and watch prices across Southeast Asian marketplaces without scraping.

This is the install packet maintainers and agent builders keep asking for. No local process. No paid directory. Copy the config.

Endpoints

Site: https://buywhere.ai
Docs: https://docs.buywhere.ai
MCP: https://api.buywhere.ai/mcp
Live write-up: https://dev.to/buywhere/buywhere-mcp-is-live-for-shopping-agents-v2-deliverto-4deh
Official MCP registry + Glama: already live
Smithery: BuyWhere remote MCP

Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "buywhere": {
      "url": "https://api.buywhere.ai/mcp"
    }
  }
}

Restart Claude Desktop. Ask: Find the cheapest Dyson V15 in Singapore and compare Shopee vs Lazada.

Cursor / other remote MCP clients

Point the client at https://api.buywhere.ai/mcp. If the client still requires a command wrapper:

{
  "mcpServers": {
    "buywhere": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.buywhere.ai/mcp"]
    }
  }
}

Why this belongs on awesome-mcp lists

Most e-commerce MCP entries scrape a single storefront. BuyWhere is a catalog MCP for agents: product search, comparison, and deal watch with a deliver_to location. That is the shopping-agent primitive, not another Amazon HTML wrapper.

If you maintain awesome-mcp-servers, the natural section is E-Commerce / Shopping. Suggested line:

BuyWhere — Remote shopping-catalog MCP (search, compare, deals) for agents. Endpoint: https://api.buywhere.ai/mcp

PRs welcome. Do not pay for directory slots.

BuyWhere is in the official MCP registry (install the shopping catalog)

BuyWhere — Thu, 17 Sep 2026 19:46:45 +0000

BuyWhere is live on the official Model Context Protocol registry and on Glama. This is the install path for shopping agents that need real product data instead of hallucinated SKUs.

Canonical install

Remote MCP: https://api.buywhere.ai/mcp (HTTP 200)
Site: https://buywhere.ai
Official registry: https://registry.modelcontextprotocol.io/v0/servers?search=buywhere
Canonical registry name: io.github.BuyWhere/buywhere-mcp
Glama: https://glama.ai/mcp/servers/buywhere/buywhere-mcp
npm: @buywhere/mcp-server

Policy claims (backable)

300M+ products
150K+ merchants with products
9 markets: SG, US, MY, ID, TH, PH, VN, AU, NZ
v2 tools require deliver_to (ISO 3166-1 alpha-2)

What agents get

search_products_v2 ranks live listings for a destination market. Empty results return emptiness_reason so the agent can retry. Listings include affiliate_redirect_url when a tracked path exists.

If you maintain an MCP client or agent runtime, point it at https://api.buywhere.ai/mcp and pass deliver_to.

BuyWhere MCP directory packet (300M+ products, remote endpoint)

BuyWhere — Tue, 15 Sep 2026 10:18:41 +0000

BuyWhere is an agent-native product catalog. One MCP endpoint gives shopping agents keyword search over 300M+ products from 150K+ merchants with products across 9 markets.

Canonical endpoint

Remote MCP: https://api.buywhere.ai/mcp (HTTP 200, name=buywhere-catalog)
Site: https://buywhere.ai
Docs: https://docs.buywhere.ai
GitHub: https://github.com/BuyWhere/buywhere-mcp
Smithery listing: https://smithery.ai/servers/partners/BuyWhere
Glama listing: https://glama.ai/mcp/servers/BuyWhere/buywhere-mcp

POST https://api.buywhere.ai/v1/auth/register
{"agent_name": "your-agent"}

Then JSON-RPC against the MCP URL with a Bearer token.

Tools (v1 + v2)

v1: search_products, get_product, compare_products, get_deals, list_categories, find_best_price, find_similar, ingest_products

v2 (require deliver_to): search_products_v2, get_product_v2, compare_products_v2, get_deals_v2, find_best_price_v2

Why this post exists

Directory maintainers and agent runtimes keep asking for a single public, copy-paste packet. This is that packet. Claims are limited to 300M+ products, 150K+ merchants with products, and 9 markets.

If you maintain an MCP / AI-tools directory and BuyWhere is missing or stale, use the URLs above — especially the remote endpoint rather than npx @buywhere/mcp-server as the only path.

BuyWhere MCP is live for shopping agents (v2 deliver_to)

BuyWhere — Mon, 14 Sep 2026 01:44:42 +0000

BuyWhere MCP is live at https://api.buywhere.ai/mcp. Policy-backed catalog: 300M+ products, 150K+ merchants, 9 markets. v2 tools require deliver_to. Docs: https://buywhere.ai/docs/guides/mcp

Build a Singapore deals watcher with BuyWhere get_deals_v2 (MCP)

BuyWhere — Wed, 02 Sep 2026 19:51:44 +0000

Agents should not scrape Shopee, Lazada, and Amazon to notice a price drop. BuyWhere MCP already normalizes those catalogs. This is a ~40-line watcher that registers a headless API key, calls get_deals_v2, and prints the cheapest live deals for Singapore.

Live MCP surface (verified 2026-09-02): 13 tools on https://api.buywhere.ai/mcp — 8 v1 + 5 v2 including get_deals_v2 and find_best_price_v2. Directories: Smithery and Glama.

1. Get a key (no email)

curl -s -X POST "https://api.buywhere.ai/v1/auth/register?verify=false" \
  -H "Content-Type: application/json" \
  -d '{"agent_name":"deals-watcher"}'

The JSON returns api_key. 1000 requests/day free. Store it as BUYWHERE_API_KEY.

2. Call get_deals_v2 over JSON-RPC

MCP is HTTP POST JSON-RPC 2.0, not SSE.

import json, os, urllib.request

KEY = os.environ["BUYWHERE_API_KEY"]
payload = {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "get_deals_v2",
        "arguments": {"country": "SG", "limit": 8},
    },
}
req = urllib.request.Request(
    "https://api.buywhere.ai/mcp",
    data=json.dumps(payload).encode(),
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer " + KEY,
    },
)
with urllib.request.urlopen(req, timeout=30) as r:
    body = json.load(r)

content = (body.get("result") or {}).get("content") or []
text = content[0]["text"] if content else json.dumps(body)
data = json.loads(text) if isinstance(text, str) and text[:1] in "[{" else text
items = data if isinstance(data, list) else data.get("deals") or data.get("products") or []

def amount(p):
    price = p.get("price") or {}
    if isinstance(price, dict):
        return price.get("amount"), price.get("currency")
    return p.get("amount"), p.get("currency")

for p in items[:8]:
    amt, cur = amount(p)
    title = p.get("title") or p.get("name")
    print(f"{cur} {amt}  {title}")

Price shape: price is nested {amount, currency}. Do not read a flat price number.

3. Cron it

Run every 30 minutes. Swap country to US for the US catalog. Pair with find_best_price_v2 when you already know the SKU.

Try it on a live page

US budget laptops (affiliate hops via /r/, never merchant URLs): best-budget-laptops-us.

Connect the same server from Claude / Cursor via Smithery or Glama — you do not need this script if your client already speaks MCP.

Build a grocery price comparison agent with BuyWhere MCP (Singapore 2026)

BuyWhere — Wed, 02 Sep 2026 17:57:40 +0000

I Let AI Agents Bid on My Groceries for a Week -- Here's What Happened

Or: how a Singapore developer accidentally built a live price-comparison swarm that never sleeps

Last Tuesday I needed to restock my HDB kitchen. Rice. Oil. Dish soap. The usual.

Instead of opening Shopee, Lazada, and FairPrice in three tabs, I thought: what if I just asked the AI?

I wrote a small script that queried BuyWhere's product catalog via MCP -- one function call, no scraping, no browser automation. It returned every merchant currently selling each item, with prices, in under 200ms.

The result surprised me.

The Setup

I had three products on my list:

T Jasmine Rice 5kg -- I buy this every 6-8 weeks
Palm Cooking Oil 1L -- basic, but which brand is cheapest right now?
Dawn Ultra Dish Soap -- brand-loyal, but is it actually the best value?

I wrote a quick Python loop:

from buywhere import mcp

def find_best(product_query, country="SG", limit=5):
    results = mcp.search_products(
        query=product_query,
        country_code="SG",
        limit=limit
    )
    return sorted(results, key=lambda x: x["price"]["amount"])[:3]

items = ["T Jasmine Rice 5kg", "Palm Cooking Oil 1L", "Dawn Ultra Dish Soap"]

for item in items:
    top_3 = find_best(item)
    print(f"\n=== {item} ===")
    for r in top_3:
        print(f"  {r['merchant_name']}: ${r['price']['amount']} {r['price']['currency']}")

What Happened

The script ran in under 1 second and returned:

=== T Jasmine Rice 5kg ===
  FairPrice: $12.80 SGD
  Sheng Siong: $12.50 SGD
  Cold Storage: $13.20 SGD

=== Palm Cooking Oil 1L ===
  NTUC FairPrice: $4.20 SGD
  Giant: $3.95 SGD
  Prime Supermarket: $4.10 SGD

=== Dawn Ultra Dish Soap ===
  Lazada (Dawn Official Store): $7.90 SGD
  Shopee: $7.50 SGD
  FairPrice: $8.20 SGD

Three supermarkets, two marketplaces, one answer.

The oil was 25 cents cheaper at Giant than FairPrice. On a 1L bottle, that's ~6%. But the bigger win was knowing I could -- I saved the script and now run it before any bulk grocery order.

Why This Matters for Developers

Here's the part that made me actually pause.

This isn't a web scraper. There's no HTML parsing, no Selenium, no Cloudflare circumvention. The data comes from the BuyWhere catalog -- a structured database with 370M+ products and 940K+ merchants.

That means you can:

Build price alerts that check live merchant data, not cached pages
Write comparison agents that actually execute (redirect to the cheapest /r/ link)
Integrate into workflows -- a Notion database, a Slack bot, a scheduled cron job
Query by country -- SG, US, MY, AU, UK -- so your agent knows the local price

The MCP interface makes this a single function call:

# Full Python MCP example
results = mcp.search_products(
    query="MacBook Air M4",
    country_code="SG",
    limit=10,
    min_price=800,
    min_price_currency="SGD"
)

The Agent Angle

Here's where it gets interesting.

If you can query prices via MCP, you can also chain that with a buying intent. BuyWhere pages already have an affiliate redirect system (/r/{merchant_id}) that tags your links. An agent that:

Searches for the cheapest product
Renders a comparison table
Redirects the user to the merchant page via /r/

...is a complete shopping agent. No scraping. No affiliate API negotiations. Just structured data and a redirect.

For developers building AI shopping assistants, price comparison tools, or deal-finding bots -- this is the infrastructure layer you didn't know existed.

What I'd Build Next

If I had another evening, I'd add:

Price history -- track the same product weekly and flag when it drops below your threshold
Multi-country comparison -- "is the US price + shipping cheaper than SG?"
Category sweeps -- "find all Samsung phones under $800 in Singapore" as a single query

The catalog is rich enough for all of this. The MCP makes it accessible to any AI agent that speaks JSON.

Try It

You can query the BuyWhere MCP server directly via curl -- no SDK install required:

curl -X POST https://api.buywhere.ai/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "search_products",
      "arguments": {
        "query": "MacBook Air M4",
        "country_code": "SG",
        "limit": 5
      }
    }
  }'

Or install the Python SDK:

pip install buywhere-mcp

The server runs locally (or on your agent's infrastructure) and connects to the BuyWhere catalog API. 13 tools, full CRUD on products, deals, merchants, and affiliate redirects.

The Bottom Line

I spent 20 minutes writing a script and now I have a personal price-comparison agent that never sleeps. It works on groceries, electronics, anything in the catalog.

For developers: this is a structured product data API with an agent-native interface. If you're building anything that involves "what's the best price for X right now," this is worth 20 minutes of your time.

The MCP server is open source. The catalog has 370M+ products. The redirect system handles affiliate tagging.

Build something with it.

Disclosure: BuyWhere is an affiliate partner -- /r/ links are revenue-generating redirects. But the catalog data is real, the prices are live, and the script above is exactly what I ran in my kitchen.

AI Agents and Grocery Shopping in 2026

BuyWhere — Wed, 02 Sep 2026 17:56:59 +0000

I Let AI Agents Bid on My Groceries for a Week -- Here's What Happened

Or: how a Singapore developer accidentally built a live price-comparison swarm that never sleeps

Last Tuesday I needed to restock my HDB kitchen. Rice. Oil. Dish soap. The usual.

Instead of opening Shopee, Lazada, and FairPrice in three tabs, I thought: what if I just asked the AI?

The result surprised me.

The Setup

I had three products on my list:

T Jasmine Rice 5kg -- I buy this every 6–8 weeks
Palm Cooking Oil 1L -- basic, but which brand is cheapest right now?
Dawn Ultra Dish Soap -- brand-loyal, but is it actually the best value?

I wrote a quick Python loop:

from buywhere import mcp

def find_best(product_query, country="SG", limit=5):
    results = mcp.search_products(
        query=product_query,
        country_code="SG",
        limit=limit
    )
    return sorted(results, key=lambda x: x["price"]["amount"])[:3]

items = ["T Jasmine Rice 5kg", "Palm Cooking Oil 1L", "Dawn Ultra Dish Soap"]

for item in items:
    top_3 = find_best(item)
    print(f"\n=== {item} ===")
    for r in top_3:
        print(f"  {r['merchant_name']}: ${r['price']['amount']} {r['price']['currency']}")

What Happened

The script ran in under 1 second and returned:

=== T Jasmine Rice 5kg ===
  FairPrice: $12.80 SGD
  Sheng Siong: $12.50 SGD
  Cold Storage: $13.20 SGD

=== Palm Cooking Oil 1L ===
  NTUC FairPrice: $4.20 SGD
  Giant: $3.95 SGD
  Prime Supermarket: $4.10 SGD

=== Dawn Ultra Dish Soap ===
  Lazada (Dawn Official Store): $7.90 SGD
  Shopee: $7.50 SGD
  FairPrice: $8.20 SGD

Three supermarkets, two marketplaces, one answer.

The oil was 25 cents cheaper at Giant than FairPrice. On a 1L bottle, that's ~6%. But the bigger win was knowing I could -- I saved the script and now run it before any bulk grocery order.

Why This Matters for Developers

Here's the part that made me actually pause.

This isn't a web scraper. There's no HTML parsing, no Selenium, no Cloudflare circumvention. The data comes from the BuyWhere catalog -- a structured database with 370M+ products and 940K+ merchants.

That means you can:

Build price alerts that check live merchant data, not cached pages
Write comparison agents that actually execute (redirect to the cheapest /r/ link)
Integrate into workflows -- a Notion database, a Slack bot, a scheduled cron job
Query by country -- SG, US, MY, AU, UK -- so your agent knows the local price

The MCP interface makes this a single function call:

# Full Python MCP example
results = mcp.search_products(
    query="MacBook Air M4",
    country_code="SG",
    limit=10,
    min_price=800,
    min_price_currency="SGD"
)

The Agent Angle

Here's where it gets interesting.

If you can query prices via MCP, you can also chain that with a buying intent. BuyWhere pages already have an affiliate redirect system (/r/{merchant_id}) that tags your links. An agent that:

Searches for the cheapest product
Renders a comparison table
Redirects the user to the merchant page via /r/

...is a complete shopping agent. No scraping. No affiliate API negotiations. Just structured data and a redirect.

For developers building AI shopping assistants, price comparison tools, or deal-finding bots -- this is the infrastructure layer you didn't know existed.

What I'd Build Next

If I had another evening, I'd add:

Price history -- track the same product weekly and flag when it drops below your threshold
Multi-country comparison -- "is the US price + shipping cheaper than SG?"
Category sweeps -- "find all Samsung phones under $800 in Singapore" as a single query

The catalog is rich enough for all of this. The MCP makes it accessible to any AI agent that speaks JSON.

Try It

You can query the BuyWhere MCP server directly via curl -- no SDK install required:

curl -X POST https://api.buywhere.ai/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "search_products",
      "arguments": {
        "query": "MacBook Air M4",
        "country_code": "SG",
        "limit": 5
      }
    }
  }'

Or install the Python SDK:

pip install buywhere-mcp

The server runs locally (or on your agent's infrastructure) and connects to the BuyWhere catalog API. 13 tools, full CRUD on products, deals, merchants, and affiliate redirects.

The Bottom Line

I spent 20 minutes writing a script and now I have a personal price-comparison agent that never sleeps. It works on groceries, electronics, anything in the catalog.

The MCP server is open source. The catalog has 370M+ products. The redirect system handles affiliate tagging.

Build something with it.

I Let AI Agents Bid on My Groceries for a Week

BuyWhere — Wed, 02 Sep 2026 17:55:32 +0000

Test body

DEV Community: BuyWhere

Smithery listing live: BuyWhere shopping MCP (partners/BuyWhere)

Install / connect

What agents get

Cursor / Claude snippet

Maintainers: 3 still-missing awesome-lists

PR packet: add BuyWhere shopping MCP to 3 awesome-lists (Sep 22)

1) appcypher/awesome-mcp-servers (E-Commerce)

2) jaw9c/awesome-remote-mcp-servers

3) wong2/awesome-mcp-servers

4) mcpfinder.com (unpaid)

Copy-paste: add BuyWhere shopping MCP to awesome-mcp-servers lists

Canonical listing packet

Suggested README row (awesome-mcp-servers)

Lists that should include a shopping / commerce MCP

60-second Claude Desktop config

Remote MCP shopping catalog — add BuyWhere to Claude, Cursor, and ChatGPT connectors

Endpoint

Claude Desktop / Cursor (2 minutes)

Why this listing exists

Suggested awesome-list row

Add BuyWhere shopping MCP to Claude Desktop and Cursor in 2 minutes

Endpoints

Claude Desktop

Cursor / other remote MCP clients

Why this belongs on awesome-mcp lists

BuyWhere is in the official MCP registry (install the shopping catalog)

Canonical install

Policy claims (backable)

What agents get

BuyWhere MCP directory packet (300M+ products, remote endpoint)

Canonical endpoint

Tools (v1 + v2)

Why this post exists

BuyWhere MCP is live for shopping agents (v2 deliver_to)

Build a Singapore deals watcher with BuyWhere get_deals_v2 (MCP)

1. Get a key (no email)

2. Call get_deals_v2 over JSON-RPC

3. Cron it

Try it on a live page

Build a grocery price comparison agent with BuyWhere MCP (Singapore 2026)

I Let AI Agents Bid on My Groceries for a Week -- Here's What Happened

The Setup

What Happened

Why This Matters for Developers

The Agent Angle

What I'd Build Next

Try It

The Bottom Line

AI Agents and Grocery Shopping in 2026

I Let AI Agents Bid on My Groceries for a Week -- Here's What Happened

The Setup

What Happened

Why This Matters for Developers

The Agent Angle

What I'd Build Next

Try It

The Bottom Line

I Let AI Agents Bid on My Groceries for a Week