AI Search Visibility Platform for Scaling Agencies
CitationBench unifies SEO and GEO workflows across your entire client portfolio — from keyword research and content production to AI citation tracking and link-building — in one platform.
# 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: 0.44claude · cited: ✓ rank: 2 share_of_voice: 0.21perplexity · cited: ✗ rank: — share_of_voice: 0.00# Schedule daily monitoring across all client workspacesresearch.ai_citation.history✓ 14-day citation trajectory returned · 3 engines trackedFragmented Tools Leave You Flying Blind
Most agencies run six or more disconnected tools and still have no answer when clients ask about AI search.
Invisible to AI Search Engines
Traditional rank trackers show Google positions but cannot tell you if ChatGPT, Claude, or Perplexity are citing your clients.
Ten Tools for One Workflow
Stitching together Ahrefs, Surfer, Apollo, Instantly, and AgencyAnalytics burns hours that could run client campaigns.
Onboarding a New Client Takes Weeks
Building keyword universes, ICPs, and content plans from scratch for each new brand delays time-to-value and strains small teams.
The fix
One Platform. Every SEO and GEO Workflow.
CitationBench composes research, content production, multi-platform publishing, indexing, link-building, and AI citation tracking into agentic workflows — all accessible via REST API, hosted MCP server, or dashboard.
Everything Your Agency Needs to Win Organic Visibility
Five integrated capabilities that cover the full research-to-rank loop, including AI search visibility that no legacy SEO platform tracks.
GEO Monitoring
Track AI Search Visibility Across All Clients
Monitor brand citations in ChatGPT, Claude, and Perplexity for any target query via research.ai_citation.check. Returns share-of-voice per engine with a 14-day citation trajectory — scoped per client workspace.
- ChatGPT, Claude, Perplexity
- Share-of-voice history
- Daily scheduled queries
Agency Architecture
One API Key for Every Client Brand
Manage all client brands under a single master API key. Every call is scoped to the correct client via X-Workspace-Id — giving you full isolation, bulk actions, and white-label-ready reporting across your entire portfolio.
- X-Workspace-Id scoping
- Bulk cross-workspace actions
- White-label ready
Agentic Workflows
Bootstrap a New Brand in 20 Minutes
POST /v1/agent/invoke runs the brand-bootstrap agent end-to-end — generating ICP profiles, a labeled keyword universe, and a content plan — pausing at configurable approval gates before any action is taken.
- 20-minute brand bootstrap
- Human approval gates
- Real-time SSE streaming
Rank Reporting
Daily Rank Tracking Across Every Client
Pull daily keyword position history for every client workspace via REST, MCP tool, or the dashboard. Bulk rank pulls across all workspaces give agencies one unified view without toggling between tools.
- Daily position updates
- Full keyword history
- Bulk cross-workspace pulls
Link Building
Turn One Keyword Into 50 Outreach Drafts
POST /v1/link-building/serp-outreach turns a single keyword into a SERP scrape, Apollo contact discovery, and 50 personalized email drafts via Instantly — all in one call. Bulk-approve before any message is sent.
- 50 drafts per keyword
- Apollo contact discovery
- Bulk approve before send
How it works
From sign-up to first call in five minutes.
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.
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.
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.
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 Search Visibility Today
CitationBench gives agencies one platform to monitor AI citations, track ranks, and run end-to-end SEO ops across every client brand.
Book a Demo