Skip to main content
Glama
Sign In
Competitor Price, Stock, and Changelog Monitor MCP Server

Competitor Price, Stock, and Changelog Monitor MCP Server

by mambalabsdev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Competitor Price, Stock, and Changelog Monitor MCP Server

Glama score MCP Registry npm version npm downloads license mcpservers.org

An MCP server for the Mamba Labs Competitor Price, Stock, and Changelog Monitor actor on Apify. Give it competitor sites. Each run compares every site with the state saved by the last run and returns only what changed.

What's Inside

Related MCP server: Competitor Website Change Monitor

What it does

  • Stores: Shopify stores through their public product feed and WooCommerce stores through their public Store API. Changes: price_change, compare_at_price_change, out_of_stock, back_in_stock, new_product, removed_product, each with the product, variant, old and new value, and a link.

  • SaaS sites: the pricing page and changelog the site links to. Changes: plan_added, plan_removed, plan_price_change, pricing_page_change, and changelog_entry.

  • One row per site per run: site_baseline on the first check under a state_key, then site_check with changes_found for a site that changed, or a free no_change row when nothing moved.

Unreadable sites come back free with a row_status saying so.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-competitor-price-stock-changelog-monitor": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-competitor-price-stock-changelog-monitor"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The monitor_competitor_changes tool appears.

Prerequisites

Example prompts

  • "Watch deathwishcoffee.com and allbirds.com for price cuts of 10 percent or more and tell me what changed since last week."

  • "Did Notion or Linear change their pricing plans or ship anything new this week?"

  • "Which products went out of stock on gymshark.com since yesterday?"

Tool

monitor_competitor_changes. One tool. Example arguments:

{
  "sites": [
    "deathwishcoffee.com",
    "linear.app"
  ],
  "state_key": "competitors-weekly",
  "min_price_change_pct": "5"
}

Inputs

Every buyer facing input of the actor, unchanged. Omitted inputs take the actor's own defaults. Numbers and booleans are sent as strings.

Input

Type

Description

sites

array

Competitor sites to watch, one per line: a domain (deathwishcoffee.com, linear.app) or a URL. A URL with a path is read as that page: a pricing page, a changelog page, or a product page. Up to 200 sites per run

site_type

string

auto (default) reads the public Shopify product feed or the WooCommerce Store API when the site has one, and otherwise reads the pricing and changelog pages it links to

watch

array

Any of: prices, stock, products, plans, changelog. prices covers price and compare at price per variant; stock covers in stock and out of stock; products covers new and removed products; plans covers plan names and prices on a pricing page; changelog covers new changelog entries. Empty means all five

product_urls

array

Product pages on a store that is not Shopify or WooCommerce. Each page is read for its schema.org Product price and availability

pricing_urls

array

Pricing pages to read, when the site does not link to its pricing page from the homepage

changelog_urls

array

Changelog or release notes pages to read, when the site does not link to one from the homepage. An RSS or Atom feed the page declares is read first

max_products

string

Products read from a store catalog per run, up to 5000. A store with more products than this is compared on the products read, and removed products are not reported for it. Default 250

min_price_change_pct

string

Report a price change only when it is at least this many percent. 0 reports every change. Default 0

max_changes_per_site

string

Change rows returned per site per run, up to 1000. The rest are counted in changes_found. Default 200

include_snapshot

string

true to also return one snapshot row per product variant, plan, and changelog entry on the first check of a site. Each snapshot row is billed as a snapshot row. Default false

state_key

string

Names the saved state, so separate schedules keep separate baselines. Runs with the same state key and site compare against each other

reset_state

string

true to ignore the saved state and record a new baseline for every site. Default false

max_charge_usd

string

Optional. The run stops before it would charge more than this

proxy_mode

string

auto (default) sends requests directly and moves a host to the Apify proxy default pool only when that host refuses. A reliability setting: proxy use adds nothing to your price

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

Event

Free plan

Bronze

Silver

Gold

change-row, one change on a watched site since the last run: a price, compare at price, or stock change on a variant, a new or removed product, a plan added, removed, or repriced, a price change on a pricing page, or a new changelog entry

$0.0025

$0.002375

$0.00225

$0.002125

site-check, the first check of a site, or a later check that finds a change

$0.003

$0.00285

$0.0027

$0.00255

snapshot-row, one current variant, plan, or changelog entry on the first check of a site, returned only when include_snapshot is on

$0.001

$0.00095

$0.0009

$0.00085

apify-actor-start, per run start

$0.0005

$0.0005

$0.0005

$0.0005

A site where nothing moved returns a free no_change row, and sites that cannot be read are free.

Your keys

The actor needs no key. It reads public product feeds and public pages and holds no key of any kind. Proxy traffic adds nothing to your price: Mamba Labs pays the platform costs of the run. proxy_mode is a reliability setting.

Full actor documentation

apify.com/mambalabs/competitor-price-stock-changelog-monitor

License

MIT. See LICENSE.

Available Tools

1 tool
monitor_competitor_changesMonitor competitor prices, stock, and changelogsA
Read-only

Watch competitor stores and SaaS sites and return only what changed since the last run with the same state_key. Give sites as domains or URLs (for example deathwishcoffee.com, linear.app). Shopify stores are read from their public product feed and WooCommerce stores from their public Store API, so you get price, compare at price, and stock changes per variant, plus new and removed products. SaaS sites are read from the pricing and changelog pages they link to, so you get plans added, removed, or repriced, and new changelog entries. Every site gets one row per run (site_baseline on the first check, then site_check with changes_found), plus one row per change with old and new values. Unreadable sites come back free with a row_status saying so. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN; Apify charges per change row and per site check that is a first check or finds a change; an unchanged site is free.

Inputs: sites (required), watch, site_type, state_key, +10 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    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

    A4.1/5.0

    Scored across 1 tool

    Disambiguation4/5

    With only one tool there is no cross-tool selection ambiguity, so an agent cannot pick the wrong tool. However, the single tool internally bundles several distinct capabilities (Shopify feed diffing, WooCommerce Store API diffing, SaaS pricing-page diffing, changelog diffing) that an agent cannot address individually, which slightly weakens clarity of purpose.

    Naming Consistency4/5

    The lone name monitor_competitor_changes is a clear snake_case verb_noun phrase in line with typical MCP conventions. With only one name there is no pattern to be inconsistent with, so it cannot score a full 5.

    Tool Count3/5

    The apparent scope (stateful competitor change monitoring) is narrow enough that a single entry point is defensible and keeps the surface simple. Still, one tool is thin for a pipeline that involves state keys, run IDs, per-site checks, and change rows—there is no way to inspect runs or manage state separately.

    Completeness3/5

    Core monitoring is covered, including change reporting and unreadable-site status, which is good. But there are notable gaps: no way to list or retrieve past runs by run ID, no way to reset or delete a state_key baseline, no way to inspect a single site's stored state, and no configuration of per-site watch rules.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • ShopSignal

      codesk90
      F
      license
      Not graded
      quality
      C
      maintenance
      DTC competitor intelligence: catalog snapshots, price history, cross-brand product comparison, and drop/restock detection for 84 Shopify-powered brands. Pay-per-call via Apify.
      -

    • CompetitorPulse

      vk-ai
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables tracking competitor websites, changelogs, blog feeds, and pricing pages with meaningful diffs, classification, and Markdown digests via MCP tools for listing, adding, removing competitors, running checks, and retrieving digests or changes.
      MIT