White Label SEO Report Engine for Agencies
Pull daily rank tracking, AI citation, and link-building data via the CitationBench API to build fully branded white label SEO reports for every client workspace.
Generic Reports Are Costing You Clients
Agency clients expect polished, branded insights. Fragmented tools make that harder than it should be.
Reports Expose Your Tool Stack
Sending AgencyAnalytics or Ahrefs-branded exports tells clients exactly which off-the-shelf tools you rely on.
Data Lives in Six Different Tabs
Rank data, AI citations, and link-building metrics sit in separate platforms with no unified API to pull from.
AI Search Is Missing Entirely
Your current reporting stack has no visibility into whether clients appear in ChatGPT, Claude, or Perplexity results.
The fix
One API. Every Metric. Fully Branded Reports.
CitationBench exposes rank tracking, AI citation share-of-voice, and link-building campaign data through a single REST API with per-client workspace isolation, so you build reports that look like yours alone.
Everything Your White Label Reports Need
Five reporting-grade capabilities — rank positions, AI citations, link pipeline, content quality scores, and workspace isolation — all accessible via one API key.
Agency Architecture
Per Client Workspace for Every Report
One master API key manages N client workspaces. All rank, citation, and link data scoped per client via the X-Workspace-Id header. Fully white-label-ready with isolated settings and campaigns.
- Single API key, N clients
- X-Workspace-Id header scoping
- White-label-ready isolation
Daily Tracking
Daily Rank Data Across All Clients
Pull per-keyword rank history for every client workspace via REST or dashboard. Bulk rank pulls across all workspaces let you populate white label SEO reports without manual exports.
- Daily rank updates per workspace
- Full keyword position history
- Bulk pulls across all clients
GEO Reporting
AI Citation Data Your Clients Cannot Get Elsewhere
Track client brand citations in ChatGPT, Claude, and Perplexity via research.ai_citation.check. Return share-of-voice and citation trajectory — metrics no traditional reporting platform provides.
- ChatGPT, Claude, Perplexity coverage
- Share-of-voice per engine
- Historical citation trajectory
Brand Consistency
Enforce Brand Voice Across Every Client
Configure reusable content refiners once per agency account and apply them automatically across all client workspaces via produce.refine.*. Removes competitor mentions, enforces tone, and inserts client CTAs.
- Configure once, apply everywhere
- Competitor mention removal
- Per-client voice enforcement
Client Trust
Approval Gates Before Anything Goes Live
Any agent workflow can pause and emit awaiting_approval so your team reviews before a client sees results. Every decision is logged and auditable. Approve via dashboard or POST /v1/agent/invocations/{id}/approve.
- Pause before client delivery
- Dashboard and API approval
- Full audit log per decision
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 Delivering Branded SEO Reports Today
Pull rank, AI citation, and link-building data via one API and build white label reports your clients will trust.
Start Free