CitationBench

LLM Share of Voice Tracking for Agencies

CitationBench tracks your brand's LLM share of voice across ChatGPT, Claude, and Perplexity daily — alongside traditional rank data — in one unified platform.

Talk to SalesRead the docs
CitationBench · AI Citation Monitor
# Measure LLM share of voice 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: 0.43claude     · cited: ✓  rank: 3  share_of_voice: 0.21perplexity · cited: ✗  rank: —  share_of_voice: 0.00# Pull citation history over timeresearch.ai_citation.history{ "trend": "up", "citations_last_30d": 18, "engines": ["chatgpt", "claude"] }

Your Clients Are Invisible to AI Search

Traditional SEO tools report on Google rankings but cannot tell you which brands AI search engines are citing instead of yours.

Leadership asks. You guess.

Clients demand to know if ChatGPT recommends their brand. No existing rank tracker answers that question.

Fragmented tools miss AI citations.

Platforms like Ahrefs and AgencyAnalytics track Google rankings but have no visibility into LLM citation data.

Competitors gain AI share unseen.

Without daily citation monitoring, rival brands can capture LLM share of voice while your team remains unaware.

The fix

One Platform. SEO and GEO measured together.

CitationBench tracks brand citations in ChatGPT, Claude, and Perplexity via research.ai_citation.check and research.ai_citation.share_of_voice — alongside daily rank tracking across every client workspace — so you never guess again.

Every Tool Your Agency Needs to Win AI Search

From AI citation monitoring to daily rank tracking and content production, CitationBench covers the full organic visibility workflow across your entire client portfolio.

Track LLM Share of Voice Daily

GEO Monitoring

Track LLM Share of Voice Daily

Monitor brand citations across ChatGPT, Claude, and Perplexity using research.ai_citation.check and research.ai_citation.share_of_voice. Historical trajectory shows how citation share moves over time per client workspace.

  • Cross-engine citation scoring
  • Historical citation trajectory
  • Per-workspace daily scheduling
Unified Rank and Citation Reporting

SEO Measurement

Unified Rank and Citation Reporting

Daily keyword rank tracking across all client workspaces via X-Workspace-Id, paired with AI citation data in one dashboard. No separate tools, no manual consolidation for client reporting.

  • Daily cross-client rank pulls
  • White-label ready output
  • Full keyword position history
See Which Brands AI Models Cite Instead

Competitive Research

See Which Brands AI Models Cite Instead

Pull competitor keyword universes and backlink profiles via research.competitor.keywords and research.competitor.overlap to understand which competing brands are earning citation share you are not.

  • Competitor keyword overlap matrix
  • Backlink profile extraction
  • AI citation gap identification
Close Gaps That Suppress Citation Share

Content Strategy

Close Gaps That Suppress Citation Share

Surface missing topics versus competitors using research.content_gap.find. Prioritized gap reports show where content investment will most directly close the LLM share of voice deficit.

  • Competitor content comparison
  • Prioritized topic gap reports
  • Stored and listable results
Manage Every Client Brand in One Place

Agency Architecture

Manage Every Client Brand in One Place

One master API key manages N client workspaces with full data isolation via X-Workspace-Id. Run citation monitoring, rank tracking, and content ops across 10 to 100 brands without switching accounts.

  • Single API key for all clients
  • Per-workspace data isolation
  • Bulk actions across workspaces

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 LLM Share of Voice Today

CitationBench gives agencies daily AI citation monitoring and rank tracking across every client brand in one platform.

Start Free