Skip to main content
Glama
justadityaraj

amazon-in-mcp

by justadityaraj
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

What it does

Three tools your LLM can call against amazon.in:

Tool

What it returns

search_amazon_in(query, max_results=5, page=1)

Ranked listings + two convenience picks: cheapest in stock and best value (rating × log10(reviews) / √price). page fetches deeper result pages.

get_product(asin_or_url)

Full product detail — price, MRP, discount, rating, reviews, stock, bullets, brand, seller, delivery

price_history_link(asin_or_url)

A Keepa.com chart URL for the amazon.in domain. No network call.

No API keys. No accounts. Runs locally over stdio. Direct HTML scraping with rotating user agents and retry on bot-check pages.

Related MCP server: Amazon & Flipkart MCP Server

Quick start

1. Install (Claude Code):

git clone https://github.com/justadityaraj/amazon-in-mcp.git
cd amazon-in-mcp && npm install && npm run build
claude mcp add amazon-in -- node "$PWD/dist/index.js"

2. Restart your MCP client (Claude Code, Cursor, Claude Desktop, etc.)

3. Ask:

"Find me a good 1TB external SSD on amazon.in under ₹10,000. Best value pick."

Your LLM will call search_amazon_in, rank by value, and hand back a real product with current price and a Keepa link for price history.

What it looks like

A real call to search_amazon_in("wireless mouse", max_results=3) returns:

{
  "query": "wireless mouse",
  "page": 1,
  "total_results": 3,
  "results": [
    {
      "asin": "B0CQRNWJM2",
      "title": "ZEBRONICS Blanc Slim Wireless Mouse...",
      "url": "https://www.amazon.in/dp/B0CQRNWJM2?tag=artech-21",
      "price_inr": 423,
      "mrp_inr": 799,
      "rating": 4.0,
      "review_count": 7801,
      "in_stock": true,
      "delivery": "FREE delivery Tomorrow",
      "price_history_url": "https://keepa.com/#!product/12-B0CQRNWJM2"
    }
  ],
  "cheapest_in_stock": { "asin": "...", "price_inr": 199, "...": "..." },
  "best_value":        { "asin": "...", "rating": 4.3, "...": "..." }
}

get_product adds bullets[], brand, seller, discount_percent, availability.

Configure your MCP client

claude mcp add amazon-in -- node /absolute/path/to/amazon-in-mcp/dist/index.js

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "amazon-in": {
      "command": "node",
      "args": ["/absolute/path/to/amazon-in-mcp/dist/index.js"]
    }
  }
}

Same JSON config as Claude Desktop. Drop it into the client's MCP settings file.

Configuration

All optional. Set these in the env block of your MCP client config; defaults preserve the original behavior.

Env var

Default

Purpose

AMAZON_IN_AFFILIATE_TAG

artech-21

Amazon Associates tag on emitted URLs. none / off / "" disables. See funding.

AMAZON_IN_CACHE_TTL_MS

90000

Lifetime of the in-memory page cache (ms). 0 disables caching.

AMAZON_IN_PROXY

unset

HTTP/HTTPS proxy URL for all requests, e.g. http://user:pass@host:8080.

Example — route through a proxy and shorten the cache to 30 s:

{
  "mcpServers": {
    "amazon-in": {
      "command": "node",
      "args": ["/path/to/dist/index.js"],
      "env": {
        "AMAZON_IN_PROXY": "http://user:pass@proxy.example:8080",
        "AMAZON_IN_CACHE_TTL_MS": "30000"
      }
    }
  }
}

Automatic routing (no need to say "use the Amazon MCP")

Once installed, the server tells your client to reach for these tools on its own. It ships MCP server instructions (returned in the initialize handshake) that instruct the model to use search_amazon_in / get_product by default for any amazon.in shopping, price, availability, or reviews question — including when you just paste an amazon.in link or an ASIN. The tool descriptions carry the same trigger keywords as a fallback for clients that read tool descriptions but not server instructions.

So you can ask "find me a mechanical keyboard under 3000" or paste a product link and the client routes to this server without you naming it. Note this is model-level guidance surfaced by the host (Claude Code, Claude Desktop, Cursor, …), not a hard protocol guarantee — a client that ignores server instructions and tool descriptions won't be forced to route.

Image search

The server intentionally doesn't accept image input — keeps it provider-agnostic. Instead, paste the image into your LLM client, ask it to describe the product, and it'll call search_amazon_in with the right keywords automatically. Works the same in every MCP-capable client.

How "best value" is scored

Among in-stock listings with at least 10 reviews:

$$ \text{score} = \frac{\text{rating} \times \log_{10}(\text{reviews} + 10)}{\sqrt{\text{price}}} $$

The highest score wins. cheapest_in_stock is just the lowest price_inr among in-stock items — useful when you want raw cheapness instead of balance.

Robustness

UA rotation

5 modern desktop UAs (Chrome / Safari / Firefox on Mac / Win / Linux)

Retries

3 attempts, exponential backoff on 5xx, 429, and bot-check pages

Bot detection

Scans first 8 KB for known CAPTCHA / robot markers

Timeout

20 s per request

Caching

Successful pages cached in memory for 90 s (per URL) to skip duplicate fetches; tune with AMAZON_IN_CACHE_TTL_MS, 0 disables

Proxy

Optional — set AMAZON_IN_PROXY to route requests through an HTTP/HTTPS proxy when a datacenter IP is blocked

State

None persisted. Stdio, no cookies, no session — the cache is a short-lived, in-process buffer only

Expect ~1–5% of requests to fail with a bot-check during heavy use. Wait 30–60 seconds and retry, run from a different network, or set AMAZON_IN_PROXY.

How this project is funded

By default, amazon.in URLs returned by this server include the author's Amazon Associates tag (artech-21). If you (or your LLM) click through and buy something, the author earns a small commission. You pay the same price. This is the only way the project stays free, MIT, and actively maintained.

Override or disable anytime with the AMAZON_IN_AFFILIATE_TAG env var:

Value

Behavior

unset

Author's tag (artech-21) — supports the project

yourtag-21

Your own Amazon Associates tag

none / off / false / ""

No tag, raw amazon.in URLs

Example — your own tag:

{
  "mcpServers": {
    "amazon-in": {
      "command": "node",
      "args": ["/path/to/dist/index.js"],
      "env": { "AMAZON_IN_AFFILIATE_TAG": "yourtag-21" }
    }
  }
}

Roadmap

  • Publish to npm so install becomes npx -y amazon-in-mcp-server

  • Optional Keepa API support (user-supplied key) for real price-history data

  • Filter helpers — min_rating, min_reviews, under_price

  • Smoke-test suite with cached HTML fixtures

Development

npm install
npm run dev      # tsx watch
npm run build    # tsc → dist/
npm start        # node dist/index.js

Test interactively with the MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Project layout:

src/
  index.ts        # MCP server + 3 tool registrations
  scraper.ts      # fetch with UA rotation, retry, bot-check, proxy, cache
  parse.ts        # cheerio selectors for search + product pages
  cache.ts        # in-memory TTL + LRU cache
  constants.ts    # UAs, headers, tuning constants, affiliate/proxy/cache config
  types.ts        # SearchResultItem, ProductDetail

Disclaimer

Fetches publicly accessible amazon.in pages for personal research and assistant use. Does not bypass authentication, paywalls, or CAPTCHAs — when Amazon serves a bot-check the tool stops and reports the error.

You are responsible for using this in line with Amazon's Terms of Service and any local laws. No warranty about uptime, accuracy, or fitness for any purpose. DOM selectors are best-effort and may break when Amazon updates its layout. PRs welcome.

License

MIT © Aditya Raj Singh

Issues, bug reports, and selector fixes welcome — Amazon's DOM shifts every few months, so this will break occasionally and need community help to keep current.

Available Tools

3 tools
get_productGet Amazon.in Product DetailA
Read-onlyIdempotent

Fetch a single amazon.in product's details by ASIN or URL.

Use this by default whenever the user pastes an amazon.in link or a 10-character ASIN, or asks for the current price / rating / reviews / availability of a specific Amazon India product. Prefer it over web search or training-data guesses.

Scrapes the product page and returns price, MRP, discount %, rating, review count, availability, bullets, brand, seller, delivery info, and a Keepa price-history URL.

Args:

  • asin_or_url (string): plain 10-char ASIN (e.g., "B0BDHWDR12") or any amazon.in product URL containing /dp/

Returns: JSON with schema: { "asin": string, "title": string, "url": string, "image": string, "price_inr": number, "price_display": string, "mrp_inr": number, "discount_percent": number, "rating": number, "review_count": number, "in_stock": boolean, "availability": string, "bullets": string[], "brand": string, "seller": string, "delivery": string, "price_history_url": string }

Error handling:

  • "Could not extract ASIN" → input was not a valid ASIN or amazon.in URL

  • "Bot-check page" → retry after a delay

ParametersJSON Schema
NameRequiredDescriptionDefault
asin_or_urlYesAmazon.in ASIN (10 chars) or any product URL containing /dp/<ASIN>

TDQS

A5/5.0
Behavior5/5

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

Annotations already indicate read-only, idempotent, open-world. Description adds that it scrapes the product page, returns specific fields, and mentions 'Bot-check page' retry. Fully discloses scraping behavior and error conditions.

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?

Well-structured with sections for purpose, usage, args, returns, error handling. Front-loaded with main purpose. Each sentence adds value, no fluff. ~200 words appropriate for detail provided.

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?

No output schema, but description provides a full JSON schema of the return value. Covers error cases. With one well-documented parameter, description is complete for correct invocation.

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

Parameters5/5

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

Input schema has one parameter with description. Tool description explains parameter format (plain ASIN or URL containing /dp/<ASIN>), examples, and constraints. Adds meaning beyond schema's basic description.

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 'Fetch a single amazon.in product's details by ASIN or URL.' It specifies the source (Amazon India) and identifiers. Distinguishes from siblings by recommending it over web search or training-data guesses.

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

Usage Guidelines5/5

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

Explicit guidance: 'Use this by default whenever the user pastes an amazon.in link or a 10-character ASIN, or asks for the current price / rating / reviews / availability.' Also says 'Prefer it over web search or training-data guesses.' Includes error handling for invalid inputs.

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

search_amazon_inSearch Amazon.inA
Read-onlyIdempotent

Search amazon.in (Amazon India) for products by keyword and return ranked listings.

Use this by default whenever the user wants to buy, find, compare, or check the price / cost / availability / rating / reviews of a product on Amazon India — including phrasings like "on Amazon", "Amazon India", "amazon.in", "find me a…", "cheapest…", or "what's the price of…". Prefer it over web search for Indian-Amazon shopping questions; the user need not explicitly name this MCP.

This tool scrapes the public amazon.in search page (no API key needed). It returns a normalised list of results plus two convenience picks:

  • cheapest_in_stock: lowest price among listings showing stock

  • best_value: weighted score = rating × log10(reviews+10) / sqrt(price), requires >=10 reviews

Args:

  • query (string, 2-200 chars): search keywords

  • max_results (int, 1-20, default 5): number of listings to return

  • page (int, 1-20, default 1): which result page to fetch; use to look past page 1

  • include_sponsored (bool, default false): include ad listings

Returns: JSON with schema: { "query": string, "page": number, // which result page was fetched "total_results": number, // listings parsed from this page (pre-slice) "returned": number, // how many are in results[] after applying max_results "results": [ { "asin": string, "title": string, "url": string, "image": string, "price_inr": number, "price_display": string, "mrp_inr": number, "rating": number, "review_count": number, "prime": boolean, "sponsored": boolean, "in_stock": boolean, "delivery": string, "price_history_url": string } ], "cheapest_in_stock": , "best_value": }

Error handling:

  • "Amazon served a bot-check page" → wait 30-60s and retry

  • "Failed to reach amazon.in" → transient network or throttling

ParametersJSON Schema
NameRequiredDescriptionDefault
pageNoResult page to fetch (1-based). Amazon shows ~16-24 organic listings per page; use this to look past the first page. Default 1.
queryYesKeyword search query (e.g., 'bluetooth speaker under 2000')
max_resultsNoMaximum listings to return (1-20). Default 5.
include_sponsoredNoInclude sponsored / ad listings. Defaults to false.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds that it scrapes the public search page (no API key), error handling details, and the computation of convenience picks (cheapest_in_stock, best_value) with formulas. No contradictions.

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?

Well-structured with clear sections: purpose, usage guidelines, internal details, args, output schema, error handling. Front-loaded with purpose and usage. Slightly lengthy but each part is justified. Could be more concise by moving output schema to a separate field.

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?

Thorough description covering all aspects: purpose, usage, parameter details, output structure, error handling, convenience picks. No output schema field exists, but the description provides full JSON schema. Appropriate for a search tool with pagination and computed fields.

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?

Input schema covers 100% of parameters with descriptions. The description adds context like query length limits, page usage explanation, and the two computed fields (cheapest_in_stock, best_value) which are derived but not parameters. Baseline is 3; this adds extra value.

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 Amazon India for products by keyword and returns ranked listings. It distinguishes from sibling tools 'get_product' and 'price_history_link' by focusing on general search. The verb 'search' and resource 'amazon.in' are specific.

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

Usage Guidelines5/5

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

Explicitly says 'Use this by default' for various shopping intents and gives example phrasings. It also states preference over web search and that the user need not name the MCP. This is comprehensive guidance.

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.

  1. 1 tool updatev0.1.3
    • Changedsearch_amazon_in1 field changed
      • addedInput schema / properties / page
        Added value: +{
+  "default": 1,
+  "description": "Result page to fetch (1-based). Amazon shows ~16-24 organic listings per page; use this to look past the first page. Default 1.",
+  "maximum": 20,
+  "minimum": 1,
+  "type": "integer"
+}
  2. 3 tool updatesv0.1.0
    • First observedget_product
    • First observedprice_history_link
    • First observedsearch_amazon_in
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

A4.4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: get_product fetches details for a specific ASIN, search_amazon_in handles keyword queries, and price_history_link builds a static URL. No overlap in functionality.

Naming Consistency4/5

Naming is mostly consistent with verb_noun pattern (get_product, search_amazon_in), but price_history_link uses a noun_noun pattern. The deviation is minor and all names are clear.

Tool Count4/5

Three tools is on the lower end but appropriate for a focused product info server. The set covers the essential operations: search, single product detail, and price history URL generation.

Completeness4/5

The tool surface covers the main workflows (search and detail fetch). A minor gap is that price_history_link only returns a URL rather than actual price history data, but the overall coverage is solid for the stated purpose.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers