White Label Rank Tracking API for Agencies
CitationBench delivers daily rank tracking across all client workspaces via a REST API with multi-workspace architecture built for white label agency reporting.
Rank Tracking Tools Were Not Built for Agencies
Bolt-on white label options cost margin, break at scale, and leave your API story unfinished.
No True API for Rank Data
Most rank trackers offer a dashboard export, not a developer-grade REST API your team can actually build on.
Client Data Bleeds Across Accounts
Tools without workspace-level isolation force manual filtering, risking one client seeing another client's data.
Rank Data Alone Is No Longer Enough
Clients are asking about AI search visibility and your current tracker has no answer for ChatGPT or Perplexity.
The fix
One API. Every Client. Fully White Label Ready.
CitationBench provides daily rank tracking scoped per client via the X-Workspace-Id header, a REST API and hosted MCP server, and AI citation monitoring alongside traditional rank data — all under your brand.
Every Feature Your Agency Needs in One API
From daily rank pulls to AI citation tracking and automated link building, CitationBench covers the full ops workflow across every client workspace.
Core Tracking
Daily Rank Tracking Across All Client Workspaces
Pull daily keyword positions for every client workspace via the REST API or MCP tool. Results scoped per client using the X-Workspace-Id header. Full position history available in bulk. White-label-ready output.
- Per-workspace rank history
- Bulk rank pulls via API
- Dashboard and REST access
Agency Architecture
Single API Key for All Client Brands
One master API key manages N client workspaces. Every rank call, keyword set, and campaign is isolated per client via X-Workspace-Id. Bulk actions operate across all workspaces simultaneously.
- N workspaces per API key
- Full workspace isolation
- White-label-ready architecture
GEO Monitoring
Track AI Citations Alongside Traditional Ranks
Monitor client brand mentions in ChatGPT, Claude, and Perplexity via research.ai_citation.check. Returns share-of-voice per engine with historical trajectory. Deliver the AI visibility report no other rank tracker provides.
- ChatGPT, Claude, Perplexity
- Share-of-voice history
- Daily citation scheduling
Client Control
Approval Gates Before Any Action Fires
Any automated workflow can pause and emit awaiting_approval before touching client assets. Approve or reject via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged and auditable.
- Human review before execution
- Auditable approval log
- Dashboard or API approval
Developer Integration
Fire Webhooks on Every Rank and Publish Event
Register per-workspace webhooks to pipe rank updates, indexing confirmations, and publish completions into your own dashboards or Slack channels. Covers agent.invocation.completed, produce.publish.completed, and indexing.url.indexed events.
- Per-workspace webhook config
- Rank and publish events
- Wire into external dashboards
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 Ranks Across All Clients
One API, full workspace isolation, and daily rank data built for white label agency reporting.
Start Free