GEO Tracking API for Unified SEO and GEO Measurement
CitationBench is a developer-grade GEO tracking API that unifies traditional rank data with AI citation monitoring across ChatGPT, Claude, and Perplexity — all via REST or hosted MCP server.
# Track GEO visibility: rank position + AI citation in one callPOST /v1/research/ai-citation> { "query": "best local SEO platform", "engines": ["chatgpt","claude","perplexity"] }chatgpt · cited: ✓ rank: 2 share_of_voice: 0.38claude · cited: ✓ rank: 4 share_of_voice: 0.21perplexity · cited: ✗ rank: — share_of_voice: 0.00# Pull traditional rank alongside GEO dataGET /v1/rank-tracking{ "keyword": "best local SEO platform", "position": 6, "workspace": "client_acme" }Standard APIs Miss the Full GEO Picture
Fragmented tools force agencies to stitch together rank data and AI visibility manually, leaving critical blind spots.
Rank Data Without AI Visibility
Tools like Ahrefs track traditional rankings but are completely blind to whether your brand appears in ChatGPT, Claude, or Perplexity results.
No Unified API Surface
Stitching rank trackers, citation monitors, and content tools across multiple APIs means duplicate data, broken workflows, and constant context-switching.
Generic APIs Lack Local Nuance
Off-the-shelf rank APIs return national averages without the intent and relevance labeling needed to make accurate geo-targeted content decisions.
The fix
One GEO Tracking API. Rank and AI Citations Unified.
CitationBench exposes a single API surface for GEO tracking: daily rank positions, AI search citation share-of-voice across ChatGPT, Claude, and Perplexity, and 2D keyword labeling — all scoped per client workspace via REST or MCP.
Everything Your GEO Tracking Stack Needs
Five integrated capabilities that cover the full GEO measurement workflow from citation monitoring to rank tracking and keyword intelligence.
GEO Measurement
AI Citation Tracking Across All Major Engines
Track brand citations in ChatGPT, Claude, and Perplexity for any target query via `research.ai_citation.check`. Returns share-of-voice per engine, citation rank, and historical trajectory — the core of any GEO tracking workflow.
- Share-of-voice per AI engine
- Historical citation trajectory
- Daily query scheduling
Traditional SEO
Daily Rank Tracking Alongside GEO Data
Monitor keyword positions daily across all client workspaces. Results scoped per client via `X-Workspace-Id`, available via REST, MCP tool, and dashboard — giving you traditional and GEO data in one place.
- Per-workspace rank history
- Bulk rank pulls across clients
- REST and MCP access
Keyword Intelligence
2D Keyword Labeling for GEO Targeting
Every keyword tagged on intent and relevance axes via `research.keyword.relabel` and `research.keyword.search`. Filter and prioritize geo-targeted keyword sets at scale without manual classification work.
- Intent and relevance axes
- Bulk relabeling support
- Filter by label downstream
Developer Access
GEO Tools via Hosted MCP Server
Access the full GEO tracking API surface through the hosted MCP server at `mcp.citationbench.com/mcp`. No self-hosting required. Connect from Claude Code, Cursor, or Windsurf and call `research.ai_citation.*` directly.
- ~35 tools, no self-hosting
- Works with Claude Code and Cursor
- research.ai_citation.* namespace
Agency Architecture
Multi-Client GEO Tracking at Scale
Manage GEO tracking across all client brands under one master API key. Every rank and citation call is scoped per client via the `X-Workspace-Id` header, with bulk actions and white-label-ready output.
- Single API key, N workspaces
- X-Workspace-Id scoping
- White-label ready
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 GEO Visibility via API
Unify rank data and AI citation monitoring across all your client workspaces with one developer-grade GEO tracking API.
View MCP Docs