Quattr

ai_visibility_competitors

Read-only

AI answer-engine (ChatGPT/Perplexity/Gemini/AI Mode) citations — NOT Google's on-SERP AI Overviews (use competitive_trends/competitive_overview for those). Use ONLY for per-COMPETITOR breakdowns (who beats us). Share of Voice, citations, mentions, and sentiment for each competitor (and you), ranked, optionally for a single search intent, AI platform, country, or device. Use for "which competitors lead us on AI visibility?" / "our AI share vs rivals by intent". If tracker is omitted, one tracker is auto-selected; multiple trackers return a picker without querying metrics. country and device filters are applied; they are not silently ignored. For your own current citation snapshot use ai_visibility_citation_audit; for trend over time use ai_visibility_trend.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "date_range": "<date_range>"
    },
    "name": "ai_visibility_competitors"
  }
}

Input Schema

Name	Required	Description
`mode`	No	DISPLAY-ONLY card mode (does not change the query): "focus" (default, top-3 named rivals + you) or "drilldown" (all tracked competitors).
`unit`	No	DISPLAY-ONLY card unit (does not change the query): "count" (default, count-first) or "pct" (percentage-first) for the citations/mentions columns.
`brand`	No	Restrict to BRANDED ("Yes") or NON-BRANDED ("No") prompts — branded prompts (e.g. "example-brand login") behave very differently from category prompts (e.g. "best web hosting"); a blended number mixes them. Omit for all prompts.
`device`	No	Optional device filter. Values are normalized to uppercase, e.g. DESKTOP or MOBILE. Applied on the same tracker-scoped AI visibility reads as country. Overview and citation audit require a tracker. If the underlying data has no device filter, the tool says so and returns no totals.
`intent`	No	Restrict to one search intent, e.g. "Informational" / "Transactional".
`country`	No	Optional country filter, e.g. "USA". Applied on tracker-scoped AI visibility reads (overview, citation audit, competitors, trend, and drilldown). Overview and citation audit require a tracker. The geography drilldown tab groups rows by country instead of filtering them. If the underlying data has no country filter, the tool says so and returns no totals.
`tracker`	No	AI Visibility tracker (unified segment id), e.g. "AI Tracker". If omitted, the only ACTIVE tracker is auto-selected; multiple trackers (or only paused ones) return a picker without querying. A paused tracker (collection stopped on its end date) is honored when named explicitly, and the result carries trackerStatus "paused" — report it as historical, not current.
`platform`	No	Restrict to one AI platform, e.g. "chatgpt" / "gemini" (platform key).
`date_range`	Yes	Explicit date range, e.g. "2026-05-01 to 2026-05-31". Both endpoints are INCLUSIVE — the END day is covered (a 7-day range = 7 days). Quattr weeks run Sunday–Saturday; for "last week" use the most recent complete Sun–Sat span.
`comparison_range`	No	Explicit comparison range for period-over-period, e.g. "2026-04-01 to 2026-04-30". Adds per-row deltas (delta + deltaPct) for the metrics; never changes which rows return (deltas are left-joined onto the selected period).

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 20, 2026

addedInput schema / properties / country

Added value: +{
+  "description": "Optional country filter, e.g. \"USA\". Applied on tracker-scoped AI visibility reads (overview, citation audit, competitors, trend, and drilldown). Overview and citation audit require a tracker. The geography drilldown tab groups rows by country instead of filtering them. If the underlying data has no country filter, the tool says so and returns no totals.",
+  "type": "string"
+}

addedInput schema / properties / device

Added value: +{
+  "description": "Optional device filter. Values are normalized to uppercase, e.g. DESKTOP or MOBILE. Applied on the same tracker-scoped AI visibility reads as country. Overview and citation audit require a tracker. If the underlying data has no device filter, the tool says so and returns no totals.",
+  "type": "string"
+}

changedInput schema / properties / tracker / description

Previous value: -"AI Visibility tracker (unified segment id). If omitted, the only tracker is auto-selected; multiple trackers return a picker."New value: +"AI Visibility tracker (unified segment id), e.g. \"AI Tracker\". If omitted, the only ACTIVE tracker is auto-selected; multiple trackers (or only paused ones) return a picker without querying. A paused tracker (collection stopped on its end date) is honored when named explicitly, and the result carries trackerStatus \"paused\" — report it as historical, not current."

First observedOct 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare read-only/non-destructive/non-open-world, yet the description adds substantial behavior: tracker auto-selection when omitted, a picker with no metric query when multiple trackers exist, paused trackers honored with trackerStatus "paused" (report as historical), and the fact that country/device filters are applied rather than silently ignored. This goes well beyond what annotations provide.

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?

Front-loads the highest-value distinction (AI answer engines, not Google AI Overviews, with the correct alternates) and stays dense throughout. It is somewhat long and repeats usage guidance via both directive and question-form examples, but no sentence is off-topic.

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?

With no output schema, the description still conveys the return shape (ranked per-competitor rows with cited metrics, per-row delta/deltaPct when comparison_range is set), the picker-without-metrics case, and the paused-tracker status caveat. Combined with the 10-parameter, fully documented schema, an agent has everything needed to invoke it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description largely restates what the schema already documents per-parameter (tracker auto-selection, country/device applied, mode/unit as display-only, comparison_range deltas), so it adds little genuinely new parameter meaning.

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?

States a specific verb+resource (per-competitor AI answer-engine share of voice, citations, mentions, sentiment, ranked) and immediately scopes it away from Google on-SERP AI Overviews by naming the sibling tools to use instead (competitive_trends/competitive_overview). It also distinguishes itself from ai_visibility_citation_audit and ai_visibility_trend by purpose. An agent can route correctly without opening any schema.

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 'Use ONLY for per-COMPETITOR breakdowns (who beats us)' plus two concrete trigger questions ('which competitors lead us on AI visibility?', 'our AI share vs rivals by intent'). It also names when to use the alternatives instead. Nothing about selection is left to inference.

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

All Quattr tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?