White Label SEO Platform for Agency Scale
CitationBench is a white label SEO platform built for agencies managing 10–100 client brands. Automate research, content, publishing, and link-building across every client workspace from one API.
Fragmented Tools Kill Agency Margins
Running client SEO across six-plus tools destroys margins, slows onboarding, and makes consistent quality impossible.
New Client Onboarding Takes Weeks
Stitching Ahrefs, Surfer, Apollo, and AgencyAnalytics together for each new client burns billable hours before work even starts.
No Consistent Brand Voice Across Clients
Without reusable content rules, every writer interprets brand guidelines differently and quality drift compounds across the portfolio.
Clients Ask About AI Search. You Have No Answer.
AgencyAnalytics and Ahrefs track traditional rankings but show nothing about ChatGPT, Claude, or Perplexity citations your clients are asking about.
The fix
One Platform. Every Client. Full SEO Ops.
CitationBench gives agencies a single white-label-ready workspace per client, automated research-to-publish workflows, reusable brand voice refiners, and AI citation tracking alongside daily rank data — all via API or dashboard.
Everything Your Agency Needs to Run at Scale
Five pillars cover the full client SEO lifecycle — from onboarding a new brand to tracking its rank and AI search citations daily.
Agency Architecture
Isolated Workspaces for Every Client Brand
One master API key manages N client workspaces. Every keyword set, content piece, campaign, and link-building pipeline is isolated per client via the X-Workspace-Id header — white-label-ready out of the box.
- X-Workspace-Id header scoping
- Bulk actions across all clients
- White-label-ready configuration
Brand Consistency
Reusable Brand Voice Rules Per Client
Define style, voice, competitor removal, CTA placement, and FAQ rules once per client workspace via produce.refine.*. Every blog post and landing page produced for that client automatically inherits those rules.
- Configure once, apply everywhere
- Competitor mention removal
- CTA and FAQ injection
Daily Monitoring
Rank Tracking Across All Client Portfolios
Track keyword positions daily across every client workspace with full history. Bulk rank pulls surface portfolio-wide movement in one view. Results scoped per client via X-Workspace-Id and accessible via REST, MCP, or dashboard.
- Daily rank checks per workspace
- Full keyword history
- Bulk pulls across all clients
GEO Visibility
AI Citation Tracking for Every Client
Monitor brand citations across ChatGPT, Claude, and Perplexity for any target query via research.ai_citation.check. Returns share-of-voice and citation history — the answer when clients ask whether they appear in AI search results.
- ChatGPT, Claude, Perplexity coverage
- Share-of-voice per query
- Historical citation trajectory
Client Control
Approval Gates Before Any Content Goes Live
Any automated agent can pause and emit awaiting_approval before publishing content or sending outreach. Clients or account managers review and approve via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged.
- Pause at any agent step
- Dashboard or 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
Run Your Entire Agency on One Platform
CitationBench gives agencies a white-label-ready SEO platform with per-client workspaces, automated workflows, and AI citation tracking.
Book a Demo