CitationBench

AI SEO Agent for Multi-Brand Agencies

CitationBench is an ai seo agent platform that automates the full workflow from research to link-building across your entire client portfolio.

Talk to SalesRead the docs
CitationBench · Bootstrap Agent
# Bootstrap a new client brand's full SEO presencePOST /v1/agent/invoke> { "agent": "brand-bootstrap", "input": { "url": "https://acme.com" } }job_id: job_9rw4m · status: running# Streaming events via SSE✓ ICP profiles generated (3 segments)✓ Keyword universe built (312 keywords labeled)✓ Content plan ready · awaiting_approval✓ Link-building campaigns queued · 50 outreach drafts

One AI Tool Cannot Do It All

Fragmented stacks slow agencies down and leave AI search visibility completely unmeasured.

Tools Stacked on Tools

Ahrefs, Surfer, Apollo, and AgencyAnalytics each do one job, forcing your team to context-switch constantly.

AI Search Is a Blind Spot

No traditional SEO platform tracks whether your clients appear in ChatGPT, Claude, or Perplexity results.

New Clients Take Weeks

Bootstrapping a new brand across research, content, and outreach manually eats days your team does not have.

The fix

One AI SEO Agent. Every Step Covered.

CitationBench composes research, content production, publishing, indexing, link-building, and AI citation tracking into durable agentic workflows. Bootstrap a new brand in 20 minutes and monitor ranks and AI citations daily across every client workspace.

Every Capability Your AI SEO Agent Needs

Five purpose-built pillars covering research, production, distribution, measurement, and agent orchestration for multi-brand agency ops.

Run End-to-End SEO Workflows Autonomously

Agent Orchestration

Run End-to-End SEO Workflows Autonomously

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

  • Brand bootstrap in 20 minutes
  • Real-time SSE job streaming
  • Approval gates at any step
Pause and Approve Before Any Action

Human in the Loop

Pause and Approve Before Any Action

Agents emit awaiting_approval at any step. Your team reviews via the dashboard or POST /v1/agent/invocations/{id}/approve, then the agent resumes exactly where it stopped. Every decision is logged.

  • Auditable approval history
  • Dashboard or API review
  • Resume from exact pause point
Track AI Search Citations Across All Clients

GEO Measurement

Track AI Search Citations Across All Clients

Monitor brand citations in ChatGPT, Claude, and Perplexity for target queries via research.ai_citation.check. Returns share-of-voice scores and historical citation trajectory per client workspace.

  • ChatGPT, Claude, Perplexity tracking
  • Share-of-voice scoring
  • Daily citation scheduling
One Keyword to 50 Outreach Drafts

Link Building

One Keyword to 50 Outreach Drafts

A single POST /v1/link-building/serp-outreach call scrapes the SERP, discovers contacts via Apollo, and generates 50 personalized email drafts via Instantly. Bulk-approve before any email sends.

  • Apollo contact discovery
  • 50 drafts per keyword
  • Bulk approve before sending
Manage Every Client Brand in One Place

Agency Architecture

Manage Every Client Brand in One Place

A single master API key manages all client workspaces. Every API call is scoped per client via the X-Workspace-Id header, with full isolation for keywords, content, campaigns, and link-building.

  • Single API key for N clients
  • Per-client workspace isolation
  • Bulk actions across workspaces

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 Running Your AI SEO Agent Today

CitationBench gives agencies and developers one platform to research, write, publish, index, link-build, and monitor AI citations across every client brand.

Book a Demo