CitationBench

LLM SEO Tool for Developers and Agencies

Generic tools lack the control you need. CitationBench delivers a full SEO and GEO workflow via REST API and hosted MCP server, with AI citation tracking built in alongside traditional rank data.

Talk to SalesRead the docs
Claude Code · CitationBench MCP
# Add CitationBench as your LLM SEO tool in Claude Code> claude mcp add citationbench --url https://mcp.citationbench.com/mcp✓ Connected · 35 tools available# Research keywords with 2D intent × relevance labelingresearch.keyword.research> { "seed": "llm seo tool", "limit": 20, "label": true }{ "kw": "llm seo api", "intent": "COMMERCIAL", "relevance": "CORE" }# Track AI citations across ChatGPT, Claude, Perplexityresearch.ai_citation.check> { "query": "best llm seo tool", "engines": ["chatgpt","claude","perplexity"] }chatgpt · cited: ✓  rank: 2  share_of_voice: 0.34

Generic SEO Tools Were Not Built for LLMs

Fragmented toolchains and fire-and-forget AI calls leave agencies and developers without the control they need.

Invisible to AI Search Engines

Tools like Ahrefs and Surfer track Google ranks but have no visibility into ChatGPT, Claude, or Perplexity citations.

No API Control for Agent Workflows

Off-the-shelf SEO platforms expose no programmable surface, forcing developers to scrape or stitch brittle integrations together.

Reliability Breaks at Scale

Fire-and-forget LLM calls fail silently, leaving long-running SEO jobs with no audit trail, no resumability, and no human review gate.

The fix

One Platform. Every SEO and GEO Workflow.

CitationBench exposes ~35 SEO and GEO tools via a hosted MCP server at mcp.citationbench.com/mcp and a REST API, covering research, content production, publishing, indexing, link building, and AI citation tracking in one unified platform.

All the Tools Your LLM SEO Agent Needs

Five purpose-built capabilities spanning research, production, distribution, and agent orchestration — all callable from your LLM agent or dashboard.

Hosted MCP Server for LLM SEO Agents

Developer Access

Hosted MCP Server for LLM SEO Agents

Connect any LLM agent to CitationBench in seconds via the hosted MCP server at mcp.citationbench.com/mcp. No self-hosting required. Works with Claude Code, Cursor, Windsurf, and ChatGPT Apps across all ~35 tools.

  • 35 tools, zero self-hosting
  • Works with Claude Code and Cursor
  • Namespaced research, produce, agent
Track AI Citations Across LLM Search Engines

GEO Monitoring

Track AI Citations Across LLM Search Engines

Monitor 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 traditional SEO tool provides.

  • ChatGPT, Claude, Perplexity tracking
  • Share-of-voice with full history
  • Daily automated citation monitoring
Keyword Research Built for Agent Pipelines

Research

Keyword Research Built for Agent Pipelines

Discover, cluster, and label keyword sets from a seed via POST /v1/research/keyword. Results persist for downstream production. Supports bulk import via research.keyword.bulk_create and downstream filtering.

  • Seed URL or list input
  • Persisted for downstream agents
  • Bulk create and relabel support
Invoke Full SEO Agents from Your LLM

Orchestration

Invoke Full SEO Agents from Your LLM

Run any named agent via POST /v1/agent/invoke with structured input. Supports real-time SSE event streaming, multi-turn continuation, and human approval gates — not fire-and-forget calls.

  • SSE real-time event streaming
  • Human approval gate pauses
  • Bootstrap full brand in 20 minutes
Durable Jobs That Survive Agent Failures

Reliability

Durable Jobs That Survive Agent Failures

All agent jobs are backed by Cyclonic workers — durable, resumable, and cancellable. Cancel via agent.invocations.cancel or resume via agent.invocations.continue. Every step is logged and auditable.

  • Survives restarts automatically
  • Cancel and resume any job
  • Full audit log per invocation

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 Building Your LLM SEO Agent Today

Connect CitationBench to your LLM agent in minutes and access 35 SEO and GEO tools via MCP or REST API.

View MCP Docs