Mcp Ai Answer Visibility Tracker

com.mambabuiltPublished by mambabuilt.comv1.0.1Updated Nov 7, 2026

Whether AI Overviews, ChatGPT, Claude, Perplexity, and Gemini name and cite a brand.

VerifiedSTDIODesktop onlyWeb Search & ScrapingBusiness & Commerce

Overview

AI-generated overview

Checks whether AI answers from Google AI Overviews, ChatGPT, Claude, Perplexity and Gemini name and cite a brand for buyer questions.

What you can do
  • Run one visibility check for a brand across a list of buyer questions
  • Ask each question several times per engine and record whether the brand was named or cited, its first-mention rank, and which competitors appeared
  • Get per-question rates with confidence ranges, top cited domains and competitor rates, plus a per-engine brand summary
  • Optionally compare against up to 20 competitors and brand aliases, and cap the run with a maximum charge
When to use it
Useful for marketing, SEO or brand teams that want to know how often AI assistants mention and link their brand for the questions buyers actually ask, and how that compares with competitors. It suits periodic visibility checks rather than one-off lookups.
Requirements
Runs locally via npx, so Node.js 18 or newer is needed. Requires an Apify account and an APIFY_TOKEN; the tool is listed without one but a call needs it. Optional OPENAI_API_KEY, ANTHROPIC_API_KEY, PERPLEXITY_API_KEY or GEMINI_API_KEY enable those engines; Google AI Overviews needs no key. Network access to Apify and the model vendors.
Before you install
Runs are billed per event to your Apify account, and model use on your own keys is billed by each vendor; max_charge_usd can cap a run. The server reads several API keys from its environment and passes them into the Apify run as secret fields, so treat the config as sensitive. Questions and brand details are sent to Apify and, for non-Google engines, to the model vendors.

Installation

In SourceWeft

  1. Open Mcp Ai Answer Visibility Tracker in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AI Answer Visibility Tracker MCP Server

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

[AI Answer Visibility Tracker MCP server]

An MCP server for the Mamba Labs AI Answer Visibility Tracker actor on Apify. Give it a brand and the questions its buyers ask. Each question is asked several times on Google AI Overviews and, on your own API keys, on ChatGPT, Claude, Perplexity, and Gemini, and every answer is checked for the brand.

What's Inside

What it does

  • Sample rows: one row per answer, with brand_named, brand_cited, first_mention_rank, competitors_named, competitors_cited, cited_domains, and an answer excerpt.
  • Rates rows: one question_summary row per question and engine, with brand_named_rate, brand_cited_rate, a 95 percent range for the named rate, the top cited domains, and each competitor's rates. One free brand_summary row per engine covers all questions.
  • Google AI Overviews with no key: shown, not_shown (no overview on the page), or deferred (Google writes the overview live and loads it after the page; free and left out of the rates).

Bad input returns one free row whose error_reason starts with input_invalid:.

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:

json
{  "mcpServers": {    "mamba-ai-answer-visibility-tracker": {      "command": "npx",      "args": [        "-y",        "@mambalabsdev/mcp-ai-answer-visibility-tracker"      ],      "env": {        "APIFY_TOKEN": "your-apify-token"      }    }  }}

Restart the client. The track_ai_answer_visibility tool appears.

To ask ChatGPT, Claude, Perplexity, or Gemini as well, add that vendor's key to the same env block: OPENAI_API_KEY, ANTHROPIC_API_KEY, PERPLEXITY_API_KEY, or GEMINI_API_KEY.

Prerequisites

  • Node.js 18 or newer.
  • An Apify API token from console.apify.com/account/integrations, set as APIFY_TOKEN. The server lists its tool without a token; a call needs one.
  • Optional: your own OpenAI, Anthropic, Perplexity, or Google AI Studio key for those engines.

Example prompts

  • "Does Google's AI Overview mention HubSpot for best crm for small business? Ask 3 times."
  • "For these 10 questions, how often do AI answers name Attio, and how often do they name HubSpot and Pipedrive?"
  • "Which sites do AI Overviews cite most for best wiki tool for a remote team?"

Tool

track_ai_answer_visibility. One tool. Example arguments:

json
{  "brand_name": "HubSpot",  "brand_domain": "hubspot.com",  "questions": [    "best crm for small business"  ],  "samples": "3",  "competitors": [    "Pipedrive|pipedrive.com",    "zoho.com"  ]}

Inputs

Every buyer facing input of the actor except the four engine keys, which come from the server environment so they never pass through the conversation. Omitted inputs take the actor's own defaults. Numbers and booleans are sent as strings.

InputTypeDescription
brand_namestringRequired. The brand to look for, as people write it. Matched as a whole word, any case
questionsarrayRequired. 1 to 50 questions buyers ask
brand_domainstringThe brand domain, such as hubspot.com. A cited page on it, or on a subdomain, counts as cited
enginesarrayAny of google_ai_overview, openai, anthropic, perplexity, gemini. Default google_ai_overview
samplesstringAsks per question per engine, 1 to 10. Default 3
competitorsarrayUp to 20, as a name, a domain, or name|domain
brand_aliasesarrayOther ways answers write the brand
country, languagestringFor Google. Default us, en
include_answer_textstringtrue (default) or false
openai_model, anthropic_model, perplexity_model, gemini_modelstringDefaults gpt-5-mini, claude-sonnet-5-5, sonar, gemini-2.5-flash
max_charge_usdstringOptional. The run stops before it would charge more than this

Pricing

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

EventFree planBronzeSilverGold
ai-overview-sample, one Google result page read for one question$0.0316$0.03002$0.02844$0.02686
answer-sample, one answer from ChatGPT, Claude, Perplexity, or Gemini on your own key$0.009$0.00855$0.0081$0.00765
question-summary, one rates row per question and engine$0.003$0.00285$0.0027$0.00255
apify-actor-start, per run start$0.001082$0.001082$0.001082$0.001082

Deferred Google samples, blocked pages, engine errors, the brand rates rows, and refused input are free.

Your keys

Google AI Overviews needs no key. ChatGPT, Claude, Perplexity, and Gemini run on your own API key, read from this server's environment and passed in the run input as a secret field. The actor sends a key only to that vendor's API and never logs, stores, or returns it. The model use is billed to you by that vendor. Mamba Labs pays the Apify platform and proxy costs of the run.

Full actor documentation

apify.com/mambalabs/ai-answer-visibility-tracker

License

MIT. See LICENSE.

Source: README.md at commit daacd4a

Tools

1

track_ai_answer_visibility

Track brand visibility in AI answers

Check whether AI answers name and cite a brand for the questions its buyers ask. Give brand_name, brand_domain, and questions (for example "best crm for small business"). Each question is asked samples times (default 3) on each engine: google_ai_overview needs no key; openai (ChatGPT), anthropic (Claude), perplexity, and gemini run on the caller's own API keys, which this server reads from its environment (OPENAI_API_KEY, ANTHROPIC_API_KEY, PERPLEXITY_API_KEY, GEMINI_API_KEY). Returns one sample row per answer (brand_named, brand_cited, first_mention_rank, competitors_named, cited_domains, answer_excerpt), one question_summary row per question and engine (brand_named_rate, brand_cited_rate with a 95 percent range, top_cited_domains, competitor rates), and one free brand_summary row per engine. Bad input returns one free row whose error_reason starts with input_invalid. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN; Apify charges per Google sample, per engine sample, and per question rates row.

Parameterscountryenginessampleslanguagequestionsrequiredbrand_namerequiredcompetitorsbrand_domaingemini_modelopenai_modelbrand_aliasesmax_charge_usd+3 more

Version history

2
  1. v1.0.1LatestNov 5, 2026
  2. v1.0.0Oct 29, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts