CitationBench

LLM Citation Monitoring for Agencies and SEO Teams

CitationBench tracks brand citations across ChatGPT, Claude, and Perplexity daily — giving agencies unified LLM citation monitoring alongside traditional rank data in one platform.

Talk to SalesRead the docs
CitationBench · AI Citation Monitor
# Monitor brand citations across all AI search enginesPOST /v1/research/ai-citation> { "query": "best SEO platform for agencies",>   "engines": ["chatgpt", "claude", "perplexity"] }chatgpt    · cited: ✓  rank: 1  share_of_voice: 0.43claude     · cited: ✓  rank: 2  share_of_voice: 0.21perplexity · cited: ✗  rank: —  share_of_voice: 0.00# Pull citation history for trend reportingresearch.ai_citation.history{ "trend": "rising", "days": 30, "citations_delta": +14 }

AI Search Is a Blind Spot

Every traditional SEO platform is invisible to AI search engines, leaving agencies without the data clients are asking for.

Leadership asks. You guess.

Clients want to know if they appear in ChatGPT responses, but no legacy rank tracker captures AI citation data.

Fragmented tools, no AI layer

Platforms like Ahrefs and AgencyAnalytics track traditional rankings but offer zero visibility into LLM citation share of voice.

Manual checks do not scale

Running citation checks query by query across multiple AI engines for dozens of client brands is not a repeatable workflow.

The fix

Daily LLM Monitoring. One Platform. Every Client.

CitationBench agents run daily LLM citation monitoring across ChatGPT, Claude, and Perplexity for every client workspace. Track share of voice, citation history, and AI rank data alongside traditional SEO metrics via REST API, MCP server, or dashboard.

Everything Agencies Need to Monitor AI Citations

Five purpose-built tools that take you from citation discovery through daily monitoring, reporting, and search visibility — all in one platform.

Daily AI Citation Tracking Across Engines

GEO Monitoring

Daily AI Citation Tracking Across Engines

Track brand citations in ChatGPT, Claude, and Perplexity for any target query. Returns share-of-voice per engine with historical trajectory via `research.ai_citation.check`, `research.ai_citation.share_of_voice`, and `research.ai_citation.history`.

  • ChatGPT, Claude, Perplexity coverage
  • Historical citation trajectory
  • Daily scheduled query monitoring
Monitor Every Client Brand in One Account

Agency Architecture

Monitor Every Client Brand in One Account

Manage LLM citation monitoring for all client brands under a single API key. Each client workspace is fully isolated via `X-Workspace-Id`, with bulk monitoring actions and white-label-ready reporting.

  • Single key, N client workspaces
  • Per-workspace citation isolation
  • Bulk monitoring across all brands
AI Citations Alongside Traditional Rank Data

Unified Measurement

AI Citations Alongside Traditional Rank Data

Daily rank tracking and LLM citation data live in the same platform. Pull both via REST or MCP tool, scoped per client workspace, so you never have to reconcile two dashboards again.

  • Daily rank and citation history
  • Per-client workspace scoping
  • REST, MCP, and dashboard access
Run Citation Monitoring as a Durable Agent

Automation

Run Citation Monitoring as a Durable Agent

Invoke a named citation monitoring agent via `POST /v1/agent/invoke` to run daily checks across all client brands automatically. Jobs are durable — they survive restarts and stream real-time events via SSE.

  • Named agent for daily monitoring
  • Durable jobs survive restarts
  • Real-time SSE event streaming
Human Approval Gates for Client Reporting

Compliance

Human Approval Gates for Client Reporting

Agents can pause at any step and emit `awaiting_approval` before surfacing citation data to clients. Every review decision is logged and auditable via the dashboard or `POST /v1/agent/invocations/{id}/approve`.

  • Configurable approval pause points
  • Full audit log of every decision
  • Dashboard or API-based approvals

How it works

From sign-up to first call in five minutes.

01

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.

02

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.

03

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.

04

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 Monitoring AI Citations Across Every Client

CitationBench delivers daily LLM citation monitoring for all your client brands alongside traditional SEO metrics in one platform.

Start Free