AI search optimization now requires tracking citations in ChatGPT, Claude, and Perplexity. CitationBench unifies traditional SEO and GEO measurement in one platform built for agencies.
# 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: 0.43claude · cited: ✓ rank: 2 share_of_voice: 0.21perplexity · cited: ✗ rank: — share_of_voice: 0.00# Pull citation history over timeresearch.ai_citation.history{ "trend": "rising", "days_tracked": 30, "citations_found": 18 }Traditional SEO platforms were not built for AI search engines, leaving brands blind to where it matters most today.
Most SEO tools track Google rankings but never tell you if ChatGPT or Perplexity is citing your brand.
Agencies juggle Ahrefs, Surfer, and Frase separately, creating manual handoffs that slow down every campaign.
Existing platforms measure either traditional rank or AI visibility but no single tool closes both in one workflow.
The fix
CitationBench tracks AI citations from ChatGPT, Claude, and Perplexity alongside traditional rank data, and automates the full workflow from keyword research through content publishing, indexing, and link building.
CitationBench composes research, production, distribution, and measurement tools into one unified platform for agencies managing AI search optimization across client portfolios.
GEO Measurement
Monitor brand mentions in ChatGPT, Claude, and Perplexity via research.ai_citation.check and research.ai_citation.share_of_voice. Daily query scheduling and historical citation trajectory included alongside traditional rank data.
SEO Research
Discover and label keyword sets from a seed URL via POST /v1/research/keyword. Every keyword tagged on intent and relevance axes, so prioritization for AI search optimization workflows is instant.
Daily Monitoring
Daily rank tracking across all client workspaces via X-Workspace-Id alongside AI citation monitoring. No toggling between separate platforms to understand how a brand performs in both traditional and AI search.
Content Production
Produce long-form SEO blog content via produce.blog_post.create with brand voice enforcement through reusable content refiners. Bulk create from keyword lists and push directly to CMS platforms.
Distribution
Every produce.publish call fires Google Search Console URL submission and IndexNow simultaneously. No manual indexing step needed after content targeting AI search optimization queries goes live.
How it works
An `sk_test_*` key lands in your dashboard instantly. No demo gate — start calling real endpoints with shape-complete responses.
`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.
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.
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
Hosted at mcp.citationbench.com/mcp. Works with Claude Code, Cursor, Claude Desktop, Windsurf, and ChatGPT Apps. No self-hosting required.
Every long-running call runs on Cyclonic workers — survives restarts, cancellable, resumable, streams via SSE. Production-safe by default.
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.
Every endpoint responds in shape-complete demo mode without auth, so you can build the agent before the user signs up.
FAQ
CitationBench gives agencies one platform to monitor AI citations, track rankings, and automate the full SEO workflow across every client.
Start Free