guzu
Guzu tracks your brand's visibility across AI platforms — ChatGPT, Perplexity, Gemini, and Google AI Overviews.
Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeCan modify data
What it can do
- Get Visibility Score: Get a brand's AI Visibility Score — how visible the brand is across AI platforms (ChatGPT, Perplexity, Gemini, AI Overview). Returns the AI Visibility Index, total citations and
- Get Results By Prompt: Get the brand's AI-visibility results broken down by individual prompt (the tracked queries), plus performance grouped by category. Use this to answer "which specific prompts/qu
- Compare Competitors: Compare the brand's AI visibility against its tracked competitors. Returns the competitor ranking (where the brand sits vs. rivals), overall market position, radar metrics, and pl
What data it sees
Do you need an account
An API key from the service settings is required
Guzu tracks your brand's visibility across AI platforms — ChatGPT, Perplexity, Gemini, and Google AI Overviews. As people increasingly ask AI assistants instead of searching Google, being cited and mentioned in AI answers is the new SEO. Guzu shows you exactly where you stand and what to fix.
What you can do:
- Prepare a brand — point Guzu at any website and it builds a tracking profile (offers, competitors, and the prompts AI users would ask).
- Start analyzing — Guzu runs those prompts across the AI platforms and records where your brand is cited, mentioned, or missing.
- Get your AI Visibility Score — a single index plus per-platform breakdown and market position vs. competitors.
- Compare competitors — see who AI assistants favor over you, overall and per platform.
- Run gap analysis — the most actionable tool: find the domains AI relies on where competitors get cited but you don't, broken down by content type, with clear off-page vs. content-strategy recommendations.
- Ask Guzu — natural-language questions about your brand's AI visibility.
Getting started:
- Create a free account at guzu.ai/mcp and copy your API key (starts with gzu_).
- Connect this server with your key.
- Ask your assistant to "prepare a brand for guzu.ai" (or any site), review the setup, and start analyzing.
Best with Claude Code, Cursor, and Windsurf. A free account includes starter credits — no credit card required.
Server tool list (8)
Raw names from tools/list. Only developers need these.
| get_visibility_score | Get a brand's AI Visibility Score — how visible the brand is across AI platforms (ChatGPT, Perplexity, Gemini, AI Overview). Returns the AI Visibility Index, total citations and mentions, the brand's market position vs. competitors, and a per-platform breakdown showing which AI platforms cite/mention the brand most. This single tool answers "how visible am I?", "which platform am I strongest on?", and "what's my market position?". Requires a brand that has finished analyzing (see check_analyzing_progress). Args: brand_id: The brand ID from your Guzu account days: Lookback window in days (default 7) |
| get_results_by_prompt | Get the brand's AI-visibility results broken down by individual prompt (the tracked queries), plus performance grouped by category. Use this to answer "which specific prompts/questions does my brand show up on, and which ones is it missing from?" Each entry shows how the brand performed for that prompt across the AI platforms. Requires a brand that has finished analyzing (see check_analyzing_progress). Args: brand_id: The brand ID from your Guzu account days: Lookback window in days (default 7) |
| compare_competitors | Compare the brand's AI visibility against its tracked competitors. Returns the competitor ranking (where the brand sits vs. rivals), overall market position, radar metrics, and platform-specific competitor rankings (who leads on each AI platform). Use this to answer "who beats me in AI answers?" and "where do I rank against competitors?". Requires a brand that has finished analyzing (see check_analyzing_progress). Args: brand_id: The brand ID from your Guzu account days: Lookback window in days (default 7) |
| ask_guzu | Ask a natural-language question about a brand's AI visibility. Gathers the most relevant visibility data for the brand and returns it so you can answer the question with specific numbers and actionable insight. Use this for open-ended questions like "why is my visibility low?" or "what should I focus on to improve?". Requires a brand that has finished analyzing (see check_analyzing_progress). Args: brand_id: The brand ID from your Guzu account question: The user's natural-language question days: Lookback window in days (default 7) |
| prepare_brand | STEP 1 of brand setup. Scan a website and build a draft AI-visibility tracking profile for review. This does NOT start tracking yet — it fetches information about the website so the user can review and edit the offers, competitors, and prompts before committing. It returns: the brand profile (name, type, value propositions), priority offers, competitors, and a set of tracking prompts (the questions Guzu will later ask the AI platforms about this brand). IMPORTANT — after calling this tool, you MUST: 1. Display ALL of these sections clearly to the user: - Brand profile (name, type, value propositions) - Priority offers (list each offer name) - Competitors (name, domain, competes_with) - Tracking prompts, broken down as: * Brand discovery queries * Branded verification queries * Per-offer: category discovery queries * Per-offer: brand offer review queries 2. Ask: "Would you like to start analyzing these as-is, or review and edit the offers, competitors, and prompts first?" 3. If they want to edit — walk them through offers, then competitors, then prompts, applying their changes to the returned data. 4. Once confirmed — call start_analyzing with the final (possibly edited) profile and tracking_questions. BEFORE calling this tool: if the user has not EXPLICITLY stated the target geography and language, you MUST ask them first. Do NOT infer or guess geography or language from the URL, domain name, currency, or page path. Ask the user "What target geography and language should I track this brand for?" and wait for their answer before calling this tool. Args: website_url: Full URL of the website (e.g. "https://example.com") geography: Target geography (e.g. "Global", "United States", "Singapore") language: Language code (e.g. "en", "fr", "de") |
| start_analyzing | STEP 2 of brand setup. Save the prepared brand and START ANALYZING it. "Analyzing" means Guzu takes each tracking prompt and asks it to the AI platforms your account covers (ChatGPT, Perplexity, Gemini, AI Overview), then records whether the brand is cited or mentioned, which competitors are cited, and which third-party domains the AI relies on. This is the step that produces all the visibility data the other tools read. You MUST have called prepare_brand first — pass the profile and tracking_questions it returned (optionally edited by the user). It returns a brand_id used by all the reporting tools. After calling this, tell the user analysis is running (it takes ~10-12 minutes) and that they can check progress with check_analyzing_progress(brand_id). Args: website_url: The website URL being tracked profile: Brand profile from prepare_brand tracking_questions: Tracking prompts from prepare_brand |
| check_analyzing_progress | Check how far along the analysis is for a brand — which AI platforms have finished collecting data and which are still processing. Show the user exactly which platforms are done and which are pending. Do NOT estimate how long the remaining platforms will take — you don't know. If platforms are still pending, ask the user to check again shortly. When everything is ready, you can call get_visibility_score, compare_competitors, get_results_by_prompt, and gap_analysis to build the full report. Args: brand_id: The brand ID returned by start_analyzing |
| gap_analysis | Find where a brand is MISSING from AI answers — the citation & domain gap analysis. This is the most actionable visibility tool. For each AI platform it shows: how often the brand is cited vs not, the overall content-type mix of what the AI cites (Blog, Listicle, Forum, Other/directories, etc.), and a ranked leaderboard of the domains the AI relies on — flagging "opportunity" domains that get cited but where the brand is absent (and, on ChatGPT and AI Overview, which of those mention rivals but not the brand). PLATFORM COVERAGE: - source="all" (default): analyzes every AI platform the account covers and returns them keyed by platform. Best for a complete picture. - source="chatgpt" | "perplexity" | "gemini" | "ai_overview" | "grok" | "claude": just that one platform, WITH full per-query breakdown. - Full gap/mention detail (mentions-you, mentions-rivals, gap pages) is only available for ChatGPT and AI Overview (has_gap_data=true). Other platforms return accurate citation frequency but not the you-vs-rival gap detail — tell the user this if they ask about gaps on those platforms. AFTER returning the data, proactively offer these follow-ups (you derive them from the data already returned — do NOT call another tool): 1. ACTION PLAN — prioritized recommendations: which opportunity domains and content types to target first (rank by cite_rate, whether rivals are cited there, and gap status). 2. PER-PROMPT GAP BREAKDOWN — walk through each prompt (the `queries` array, available in single-source mode): where the brand is cited, where rivals are cited, and the specific gap pages for that prompt. If the user wants this and you fetched source="all", re-run gap_analysis for the one platform they care about to get the per-query detail. 3. OFF-PAGE STRATEGY vs CONTENT STRATEGY — split the opportunity domains by content_type: * CONTENT STRATEGY (work done ON the client's own site): opportunities where the cited source is article/content the client could publish themselves — content_type in {Blog, Listicle, News/Editorial, Video}. The play: write that content on their own site to earn the citation. * OFF-PAGE STRATEGY (work done on THIRD-PARTY sites): opportunities where the cited source is a third-party listing/mention the client can't self-publish — content_type in {Other, Forum, Social, LinkedIn}. The play: get listed / mentioned / cited on those sources (directories, profiles, outreach). Args: brand_id: The brand ID from your Guzu account source: "all" (default) or one of chatgpt, perplexity, gemini, ai_overview, grok, claude days: Lookback window in days (default 7) |