CitationBench

AI Search Visibility Metrics You Can Actually Track

CitationBench tracks your brand's AI search visibility metrics across ChatGPT, Claude, and Perplexity alongside traditional rank data — all in one platform.

Talk to SalesRead the docs
CitationBench · AI Citation Monitor
# Check brand visibility across AI search enginesPOST /v1/research/ai-citation> { "query": "best SEO platform for agencies", "engines": ["chatgpt", "claude", "perplexity"] }chatgpt    · cited: ✓  rank: 1  share_of_voice: 0.41claude     · cited: ✓  rank: 3  share_of_voice: 0.18perplexity · cited: ✗  rank: —  share_of_voice: 0.00# Pull citation history for trend reportingresearch.ai_citation.history{ "trend": "rising", "first_cited": "2025-01-04", "engines": 2 }

Every SEO Platform Is Blind to AI Search

Rankings alone no longer tell the full story. Brands living in AI answers are invisible to traditional tools.

Rankings hide your AI presence

A brand ranking on page two can dominate ChatGPT answers. Your current rank tracker will never show you that.

Leadership asks. You guess.

Clients and boards ask whether they appear in AI search. Without citation data, every answer is speculation.

SEO and GEO data live in silos

Tools like Profound track AI citations but leave you stitching results into separate rank trackers and reporting dashboards.

The fix

SEO and GEO measured together. One platform.

CitationBench tracks AI search citations from ChatGPT, Claude, and Perplexity alongside daily keyword rankings — using research.ai_citation.check, share_of_voice, and history — so you prove impact across both traditional and AI search without switching tools.

Built to Measure What AI Search Actually Shows

Five capabilities that close the loop between traditional SEO metrics and AI search visibility, from citation tracking through rank monitoring.

Track AI Citations Across All Three Engines

GEO Measurement

Track AI Citations Across All Three Engines

Monitor your brand's presence in ChatGPT, Claude, and Perplexity for target queries via research.ai_citation.check. Returns share-of-voice per engine, citation rank, and a historical trajectory so you can report trend lines, not just snapshots.

  • Share-of-voice per AI engine
  • Citation history and trend data
  • Daily automated query scheduling
Daily Rank Tracking Alongside Citation Data

SEO Measurement

Daily Rank Tracking Alongside Citation Data

Track keyword positions across all client workspaces daily. Results scoped per client via X-Workspace-Id and available via REST, MCP tool, and dashboard — giving you traditional and AI visibility metrics in a single view.

  • Daily per-keyword rank history
  • Multi-workspace client isolation
  • REST and dashboard access
Build the Keyword Universe Behind Your Metrics

Research

Build the Keyword Universe Behind Your Metrics

POST /v1/research/keyword discovers, clusters, and labels keyword sets from a seed URL. Feeds directly into both rank tracking and AI citation monitoring so every metric is anchored to a deliberate keyword strategy.

  • Seed-to-cluster keyword discovery
  • Persists for downstream tracking
  • Bulk import and management
Prioritize Keywords by Intent and Relevance

Taxonomy

Prioritize Keywords by Intent and Relevance

Every keyword is tagged on two axes: intent (informational, commercial, transactional, navigational) and relevance (core, adjacent, tangential). Filter and prioritize which terms to monitor for AI citations versus rank tracking.

  • 2D intent and relevance tagging
  • Filter by label at scale
  • Downstream tracking integration
Manage All Client Visibility Metrics in One Place

Agency Architecture

Manage All Client Visibility Metrics in One Place

A single master API key manages N client workspaces. All AI citation and rank data is isolated per client via X-Workspace-Id, with bulk actions and unified reporting across your entire portfolio without mixing client data.

  • Per-client workspace isolation
  • Bulk cross-workspace reporting
  • Single API key for all clients

How it works

From sign-up to first call in five minutes.

01

Sign up and get your key

An `sk_test_*` key lands in your dashboard instantly. No demo gate — start calling real endpoints with shape-complete responses.

02

Add the MCP server or hit REST

`claude mcp add citationbench https://mcp.citationbench.com/mcp` from Claude Code, Cursor, or any MCP client. Or `curl` against `api.citationbench.com/v1/*` directly.

03

Run a tool or invoke an agent

Every tool returns shape-complete demo data without auth, so your agent works before the user signs up. Tools across research, production, indexing, link-building, and agents.

04

Scope to a workspace and ship

Add `X-Workspace-Id: ws_***` to scope per client. Switch to a live `sk_live_*` key when you're ready. Same API surface, same SDK.

Why CitationBench

Built for production, agency-scale, and AI-agent-first.

~35 tools, one MCP server

Hosted at mcp.citationbench.com/mcp. Works with Claude Code, Cursor, Claude Desktop, Windsurf, and ChatGPT Apps. No self-hosting required.

Durable jobs, not fire-and-forget

Every long-running call runs on Cyclonic workers — survives restarts, cancellable, resumable, streams via SSE. Production-safe by default.

Multi-workspace from day one

One master API key, N client workspaces. Switch with a single `X-Workspace-Id` header. Per-client data isolation, bulk ops across all of them.

Demo mode out of the box

Every endpoint responds in shape-complete demo mode without auth, so you can build the agent before the user signs up.

FAQ

Common questions

Start Tracking Your AI Search Visibility

Prove your brand's presence across ChatGPT, Claude, and Perplexity alongside traditional rankings — all from one platform.

Start Free