API for Rank Tracking That Scales With Your Agency
CitationBench provides a single REST API for daily rank tracking across all your client workspaces, plus AI citation monitoring that no standalone rank tracker offers.
Rank Tracking APIs Break at Agency Scale
Most rank tracking APIs were built for single-site users, not agencies managing dozens of client portfolios.
One API key per client
Most rank tracking APIs force separate credentials per domain, multiplying integration overhead as your client roster grows.
Rank data without AI search
Traditional rank trackers are blind to ChatGPT, Claude, and Perplexity — the channels your clients are now asking about.
Fragmented reporting across tools
Pulling rank data from one API and AI visibility from another means two pipelines to maintain and two dashboards to reconcile.
The fix
One API. Rank Data and AI Citations Together.
CitationBench delivers daily rank tracking across every client workspace via a single REST API, with X-Workspace-Id scoping per client. AI citation tracking from ChatGPT, Claude, and Perplexity runs alongside traditional rank data in the same platform.
Everything Your Rank Tracking API Should Do
From daily position monitoring to AI citation share-of-voice, these five capabilities cover the full measurement workflow agencies need.
Core Tracking
Daily Rank Tracking Across All Client Workspaces
Pull per-keyword rank history for any client via the REST API using the X-Workspace-Id header. Bulk rank pulls across all workspaces in one call. Also accessible via MCP tool and dashboard.
- Daily position updates
- Per-workspace keyword history
- Bulk cross-client pulls
AI Visibility
AI Citation Monitoring Alongside Rank Data
Track brand citations in ChatGPT, Claude, and Perplexity for target queries via research.ai_citation.check. Returns share-of-voice and historical citation trajectory — data no rank-only API provides.
- ChatGPT, Claude, Perplexity
- Share-of-voice scoring
- Historical citation trajectory
Agency Architecture
Single API Key for All Client Workspaces
One master API key scopes all calls per client via the X-Workspace-Id header. Workspace-level isolation for keywords, rank history, and settings. White-label-ready and built for portfolios of 10 to 100 brands.
- X-Workspace-Id scoping
- Isolated client data
- White-label ready
Developer Tools
Typed SDK for Rank Data Integration
The official @citationbench/sdk TypeScript client gives full type coverage over every rank tracking endpoint, so you can build reporting pipelines without raw REST calls or manual type wrangling.
- Full TypeScript type coverage
- Works alongside REST API
- Python SDK coming next
Automation
Webhook Events for Rank and Citation Updates
Register per-workspace webhooks to fire on indexing confirmations, agent completions, and publish events. Wire CitationBench rank and citation data directly into your reporting dashboards or Slack.
- Per-workspace registration
- Agent completion events
- Downstream dashboard integration
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 Rankings Across Every Client
One REST API for daily rank and AI citation tracking across your entire client portfolio, with per-workspace isolation built in.
Start Free