CitationBench

ChatGPT Brand Mentions Tracking for Agencies

Monitor how ChatGPT, Claude, and Perplexity cite your clients' brands. CitationBench tracks AI citation share-of-voice daily alongside traditional rank data in one platform.

Talk to SalesRead the docs
CitationBench · AI Citation Monitor
# Track a client brand across AI search enginesPOST /v1/research/ai-citation> { "query": "best project management software", "engines": ["chatgpt","claude","perplexity"] }chatgpt    · cited: ✓  rank: 2  share_of_voice: 0.38claude     · cited: ✓  rank: 4  share_of_voice: 0.21perplexity · cited: ✗  rank: —  share_of_voice: 0.00# Pull historical citation trajectoryresearch.ai_citation.history{ "brand": "Acme", "trend": "up", "delta_30d": +0.12 }

Traditional Tools Miss AI Search

Most monitoring platforms were built for web search and are blind to how AI engines mention brands.

Invisible in AI Responses

Tools like Ahrefs and AgencyAnalytics have no visibility into whether ChatGPT or Claude cite your clients at all.

No Share of Voice Data

Clients ask which AI engines mention them most. You have no data to answer with confidence.

Reputation Risks Go Undetected

A negative or missing brand citation in ChatGPT can influence buying decisions before you ever notice.

The fix

AI Citation Tracking Built for Client Portfolios

CitationBench tracks brand mentions across ChatGPT, Claude, and Perplexity daily. Monitor share-of-voice per AI engine, review citation history, and manage every client brand from one multi-workspace platform.

Every Tool Your Agency Needs to Track AI Citations

CitationBench covers the full GEO monitoring workflow from AI citation tracking and competitor intelligence to rank tracking and multi-client workspace management.

Track Brand Mentions Across AI Engines

GEO Monitoring

Track Brand Mentions Across AI Engines

Monitor client brand citations in ChatGPT, Claude, and Perplexity for target queries. Returns share-of-voice per engine with historical trajectory via research.ai_citation.check, research.ai_citation.share_of_voice, and research.ai_citation.history.

  • ChatGPT citation detection
  • Share-of-voice by engine
  • 30-day citation history
Daily Rank Tracking Alongside AI Citations

Traditional SEO

Daily Rank Tracking Alongside AI Citations

Run daily rank tracking across all client workspaces via REST, MCP tool, or dashboard. Scoped per client with X-Workspace-Id so traditional and AI search data live side by side.

  • Daily automated rank pulls
  • Per-client workspace isolation
  • Unified SEO and GEO view
Manage Every Client Brand in One Place

Agency Architecture

Manage Every Client Brand in One Place

One master API key manages all client brands. All citation and rank data scoped per client via X-Workspace-Id header with workspace-level isolation for keywords, campaigns, and reporting.

  • Single API key for all clients
  • Per-client data isolation
  • Bulk actions across workspaces
See Which Competitors AI Engines Favor

Competitive Research

See Which Competitors AI Engines Favor

Add competitor URLs to pull keyword universes and understand which brands AI engines consistently cite over your clients. Uses research.competitor.keywords and research.competitor.overlap to surface citation gaps.

  • Competitor keyword overlap
  • Backlink universe import
  • Citation gap identification
Human Review Before Any Action Goes Live

Client Compliance

Human Review Before Any Action Goes Live

Agent workflows pause at configurable approval gates before publishing or outreach sends. Clients or account managers review and approve via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged.

  • Configurable approval gates
  • Full audit trail
  • Dashboard or API approval

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 Client Brand Mentions in ChatGPT

Monitor how AI engines cite your clients daily and give them the GEO visibility data no traditional tool provides.

Start Free