CitationBench

AI Citation Tracking API for SEO and GEO Teams

Monitor brand mentions in ChatGPT, Claude, and Perplexity alongside traditional rank data. One AI citation tracking API that unifies SEO and GEO measurement in a single call.

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 analysisresearch.ai_citation.history{ "days": 30, "trend": "rising", "engines": 3 }

Traditional SEO Tools Miss AI Search

Every major SEO platform was built before AI search existed, leaving a critical visibility gap you cannot afford.

Blind to AI Search Results

Ahrefs and Semrush track Google rankings but have no visibility into ChatGPT, Claude, or Perplexity citations.

Fragmented Data Across Tools

AI citation data lives in separate tools from rank data, forcing manual reconciliation and incomplete client reports.

Leadership Asks. You Guess.

Clients and boards want to know if they appear in AI search. Without citation tracking, you have no answer.

The fix

One API. SEO and GEO in One Call.

CitationBench tracks AI citations in ChatGPT, Claude, and Perplexity via the same API surface as traditional rank tracking. Use research.ai_citation.check, share_of_voice, and history endpoints to monitor, trend, and report brand visibility across every search surface.

Everything Your AI Citation Workflow Needs

From citation monitoring and share-of-voice trending to rank tracking and content gap analysis, these tools cover the full GEO and SEO measurement loop.

AI Citation Tracking Across Three Engines

GEO Monitoring

AI Citation Tracking Across Three Engines

Track brand citations in ChatGPT, Claude, and Perplexity for any target query. research.ai_citation.check returns share-of-voice per engine. research.ai_citation.history surfaces citation trajectory over time.

  • ChatGPT, Claude, Perplexity
  • Share-of-voice trending
  • Daily citation scheduling
Daily Rank Tracking Alongside Citation Data

SEO Measurement

Daily Rank Tracking Alongside Citation Data

Daily rank tracking scoped per client workspace via X-Workspace-Id. Pairs directly with AI citation data so you report traditional and AI search performance in one unified view.

  • Per-keyword rank history
  • Multi-workspace bulk pulls
  • REST, MCP, and dashboard
MCP Server with Citation Tools Built In

Developer Access

MCP Server with Citation Tools Built In

The hosted MCP server at mcp.citationbench.com/mcp exposes research.ai_citation.* tools alongside all other SEO tools. Callable from Claude Code, Cursor, Windsurf, and ChatGPT Apps with no self-hosting required.

  • ~35 tools, no self-hosting
  • Works with Claude Code and Cursor
  • research.* namespace included
Manage Every Client Citation in One Place

Agency Architecture

Manage Every Client Citation in One Place

One master API key manages citation tracking across all client workspaces. Scope every research.ai_citation call to the correct client via the X-Workspace-Id header. White-label-ready for agency reporting.

  • Single API key, N workspaces
  • X-Workspace-Id scoping
  • Bulk actions across clients
Typed SDK for Citation API Integration

SDK Integration

Typed SDK for Citation API Integration

The official @citationbench/sdk gives TypeScript and Node developers a fully typed client for all AI citation and rank tracking endpoints. Integrate citation data into existing SEO dashboards without raw REST overhead.

  • Full TypeScript type coverage
  • @citationbench/sdk on npm
  • Works alongside MCP server

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 AI Citations Today

Monitor brand mentions in ChatGPT, Claude, and Perplexity alongside traditional rank data in one unified API.

Start Free