Vantage

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/vantagemcp-dev-vantage

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

10 read · 0 write · 0 deleteRead-only

Secrets

None asked for

Install scripts

Nothing to install (hosted)

Runs as

Hosted (remote endpoint)

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• analyze_citation_coverageCheck if AI cites your site

  Check which of several prompts/keywords actually cite a specific domain, and which ones don't. It answers "out of everything we care about, where do we already show up, and where are we invisible"; its not_cited list is the set of keywords worth a closer look. Read-only for the caller, safe to retry. Costs 1 quota unit per keyword per sample (1 sample by default; free tier is 30 units/month shared across every metered tool, so up to 30 keyword checks that period if nothing else is used). A per-keyword provider error doesn't fail the whole call - that keyword's entry just carries an "error" fi…

• analyze_citation_gapCompare your page with the cited answer

  Compare your own page's structure against the AI-generated answer actually cited for this keyword, and return a fix brief: ordered rewrite instructions for your page, not just a description of the winner. Use this to answer 'what should I change on this page to get cited' rather than only 'what does a winning answer look like'. The fix brief never contains the cited answer's text. Read-only: no side effects, safe to retry. Costs 1 quota unit/call (free tier is 30 units/month shared across every metered tool, so up to 30 calls to this tool alone if nothing else is used that period). Returns: …

• analyze_citation_structureAnalyze a winning AI answer

  Analyze the structural shape of the AI-generated answer actually cited for a keyword: does it lead with a list, how long is the opening passage, how many sources does it cite and from which domains. Use this to understand what a winning AI-search answer looks like for a topic, e.g. before writing content meant to get cited. Read-only: no side effects, safe to retry. Costs 1 quota unit per sample (1 by default; free tier is 30 units/month shared across every metered tool, so up to 30 single-sample calls to this tool alone if nothing else is used that period). Returns: {"keyword", "engine", "m…

• analyze_citation_structure_batchAnalyze winning AI answers in bulk

  Analyze the structural shape of the winning AI answer across several related keywords/topics in one call: does each lead with a list, how long is the opening, how many sources it cites. It covers a topic cluster in one call, for content planning across related pieces. Read-only: no side effects, safe to retry. Costs 1 quota unit per keyword in the batch (free tier is 30 units/month shared across all the metered tools, so up to 30 keywords total that period if nothing else is used). A per-keyword provider error doesn't fail the whole batch - that keyword's entry just carries an "error" field i…

• analyze_citation_trendTrack a site's AI citations over time

  Track how a domain's AI-citation count has moved month over month, so you can see whether visibility is growing or fading instead of only ever checking a single point in time. Use this to answer 'is our AI visibility improving' or 'did that content push actually move the needle'. Pass compare_domains to put competitors' trends next to it. Read-only: no side effects, safe to retry. Costs 1 quota unit per domain (the main domain plus each one in compare_domains; free tier is 30 units/month shared across every metered tool, so up to 30 single-domain calls to this tool alone if nothing else is us…

• find_citation_leadersFind who AI cites for a question

  Find which domains dominate AI-answer citations for a topic/keyword, and optionally check where one domain, or several competitors at once, show up among them. Use this to answer 'who's winning AI search for this topic' or 'is my competitor cited more than me for X'. Comparing several domains costs the same single call. Read-only: no side effects, safe to retry. Costs 10 quota units/call (free tier is 30 units/month shared across every metered tool, so up to 3 calls to this tool alone if nothing else is used that period). Returns: {"keyword", "platform", "top_domains" (list of {"domain", "me…

• find_cited_questionsFind questions AI cites your site for

  Find the questions people ask AI answer engines where a domain is already cited as a source, most-asked first. Starts from the domain, so nobody has to guess keywords first. Use this to answer 'what does ChatGPT already cite us for' or to pick the keywords to feed analyze_citation_coverage and analyze_citation_gap. Read-only: no side effects, safe to retry. Costs 10 quota units/call (free tier is 30 units/month shared across every metered tool, so up to 3 calls to this tool alone if nothing else is used that period). Returns: {"domain", "platform", "country", "language", "total_questions" (i…

• get_check_historyShow your past citation checks

  Read back your own earlier analyze_citation_coverage results for a domain, newest first, to show progress over time or to confirm whether a change (a rewrite, a new mention somewhere) moved anything. Use this for 'has our citation status changed since last week' without spending units. Pass `page` to follow ONE page's citations over time instead of the whole domain's. Costs 0 quota units: it only reads Vantage's own record of your checks, never the data provider. Results are kept 180 days per API key and are only visible to that key. Returns: {"domain", "keyword" (or null for every keyword),…

• get_supported_optionsList supported engines and markets

  List which AI engines, platforms and markets each Vantage tool accepts, and the per-call limits, so you can pick valid arguments before spending any quota. Use this to answer 'does Vantage cover Gemini in Italy' or 'what can I pass as engine or platform'. Costs 0 quota units - a fixed list, it never touches the data provider. Returns: {"live_answer": {"tools" (analyze_citation_coverage, analyze_citation_structure, analyze_citation_structure_batch, analyze_citation_gap), "engines" (the values for `engine`), "country" (any country name the provider accepts; for perplexity one of "perplexity_co…

• get_usageCheck remaining monthly units

  Check how much of this billing period's quota is left, before spending any of it. Use this to answer 'how many checks do I have left' or to decide whether a batch call will fit before running it. Costs 0 quota units - this never touches the paid data provider, it only reads Vantage's own record of what has been used. Returns: {"tier", "period" (YYYY-MM), "units_used", "units_limit", "units_remaining"}. find_citation_leaders and find_cited_questions cost 10 units/call; analyze_citation_trend, analyze_citation_structure (and its batch form, per keyword), analyze_citation_coverage (per keyword)…

Signals

Stars

0

Forks

1

Open issues

0

Last commit

Oct 19, 2026 (11 days ago)

Last release

Oct 19, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

dev.vantagemcp/vantage

Version

1.11.1

Auth

Auth not stated

License

MIT

Repository

github.com/vantagemcp/vantage-mcp

Website

vantagemcp.dev

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql