CitationBench

API for AI Search Visibility Track Citations Daily

Generic APIs miss AI citations entirely. CitationBench delivers a developer-grade REST API and hosted MCP server to monitor brand mentions across ChatGPT, Claude, and Perplexity alongside traditional rank data.

Talk to SalesRead the docs
CitationBench API · AI Citation Monitor
# Check brand visibility across AI search enginesPOST /v1/research/ai-citation> { "query": "best SEO platform for agencies",>   "engines": ["chatgpt", "claude", "perplexity"] }chatgpt    · cited: ✓  rank: 1  share_of_voice: 0.41claude     · cited: ✓  rank: 3  share_of_voice: 0.18perplexity · cited: ✗  rank: —  share_of_voice: 0.00# Schedule daily monitoring via REST or MCPresearch.ai_citation.history{ "trend": "rising", "days_tracked": 30, "citations": 24 }

Generic APIs Are Blind to AI Search

Most APIs track organic rankings but return nothing on how AI engines cite your brand.

No AI citation data returned

Ahrefs and Semrush APIs return zero data on ChatGPT, Claude, or Perplexity citations for any query.

Fragmented tools, no unified signal

Stitching rank trackers, citation monitors, and outreach tools creates brittle pipelines that break under real agency workloads.

Manual monitoring does not scale

Checking AI search mentions by hand across dozens of client brands is unsustainable and produces inconsistent results.

The fix

One API. SEO and GEO visibility measured together.

CitationBench exposes AI citation tracking, daily rank monitoring, keyword research, and link-building automation through a single REST API and hosted MCP server at mcp.citationbench.com/mcp, with multi-workspace scoping for every client brand.

Every Tool Your API Needs for AI Visibility

Five purpose-built capabilities covering AI citation tracking, keyword research, rank monitoring, agentic workflows, and multi-client architecture in one API surface.

AI Citation Tracking Across Search Engines

GEO Monitoring

AI Citation Tracking Across Search Engines

Track brand citations in ChatGPT, Claude, and Perplexity via POST /v1/research/ai-citation. Returns share-of-voice per engine, citation rank, and 30-day history via research.ai_citation.history. Schedule daily queries per workspace.

  • ChatGPT, Claude, Perplexity coverage
  • Share-of-voice history
  • Daily query scheduling
Daily Rank Tracking Across All Workspaces

SEO Monitoring

Daily Rank Tracking Across All Workspaces

Pull per-keyword rank history across every client workspace via X-Workspace-Id. Available through REST, the MCP tool layer, and the dashboard. Unified alongside AI citation data for complete organic visibility reporting.

  • Per-keyword daily history
  • Multi-workspace scoped pulls
  • REST and MCP access
Hosted MCP Server for AI Agent Workflows

Developer Access

Hosted MCP Server for AI Agent Workflows

Connect to mcp.citationbench.com/mcp from Claude Code, Cursor, or any MCP client. All ~35 tools available instantly with no self-hosting. Namespaced as research.*, produce.*, and agent.* for clean agent orchestration.

  • 35 tools, no self-hosting
  • Claude Code and Cursor ready
  • research.ai_citation MCP tools
Durable Citation Monitoring Jobs That Persist

Reliability

Durable Citation Monitoring Jobs That Persist

Agent jobs run on Cyclonic workers — they survive restarts, stream events via SSE, and support cancel and resume via agent.invocations.cancel and agent.invocations.continue. Not fire-and-forget polling scripts.

  • Survives process restarts
  • SSE event streaming
  • Cancel and resume support
One API Key for Every Client Workspace

Agency Architecture

One API Key for Every Client Workspace

Scope all AI citation and rank data per client using the X-Workspace-Id header on a single master API key. Workspace-level isolation for queries, history, and settings keeps client data clean and reportable.

  • Single master API key
  • X-Workspace-Id scoping
  • Bulk cross-workspace actions

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 Tracking AI Search Visibility Today

CitationBench gives developers and agencies one API to monitor brand citations across ChatGPT, Claude, and Perplexity alongside traditional rankings.

View MCP Docs