CitationBench

AI SEO Automation to Scale Your Client Portfolio

CitationBench automates end-to-end SEO workflows — from keyword research to link-building outreach — so agencies can manage more clients without adding headcount.

Talk to SalesRead the docs
CitationBench · Bootstrap Agent
# Bootstrap a new brand's full SEO presencePOST /v1/agent/invoke> { "agent": "brand-bootstrap", "input": { "url": "https://acme.com" } }job_id: job_9tz4m · status: running# Streaming events via SSE✓ ICP profiles generated (3 segments)✓ Keyword universe built (312 keywords labeled)✓ Content plan ready · awaiting_approval# Human approval gate before publishingPOST /v1/agent/invocations/job_9tz4m/approve✓ Approved · agent resuming · publishing 12 pages

Fragmented Tools Are Killing Your Margins

Stitching together six tools to run one client campaign leaves teams slow, error-prone, and unable to scale.

Too Many Tools to Manage

Running Ahrefs, Surfer, Apollo, Instantly, and AgencyAnalytics separately means constant context-switching and lost time between client campaigns.

Onboarding New Clients Takes Weeks

Manually setting up keyword research, content briefs, and outreach campaigns for each new client delays revenue and strains small teams.

No Visibility Into AI Search Results

Traditional rank trackers miss AI search engines entirely. Clients ask if they appear in ChatGPT or Perplexity and you have no answer.

The fix

One Platform. Every Step of SEO Ops.

CitationBench composes research, content production, publishing, indexing, link building, and AI citation tracking into automated workflows. Bootstrap a new client brand in 20 minutes and run daily monitoring across your entire portfolio.

Everything Your Agency Needs in One Platform

Five capability layers — research, production, distribution, agents, and reporting — purpose-built for agencies running multiple client brands.

Automate Full SEO Campaigns End to End

Agentic Workflows

Automate Full SEO Campaigns End to End

Run any named agent via POST /v1/agent/invoke with structured input. The brand-bootstrap agent takes a client URL and delivers a complete keyword universe, ICP profiles, and content plan in 20 minutes.

  • 20-minute brand bootstrap
  • SSE real-time event streaming
  • Multi-turn agent continuation
Keep Clients in Control at Every Step

Human Oversight

Keep Clients in Control at Every Step

Agents pause and emit awaiting_approval at any step. Reviewers approve or reject via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged and auditable — no blind automation.

  • Pause at any workflow step
  • Approve via dashboard or API
  • Full audit trail per client
Turn One Keyword Into 50 Outreach Drafts

Link Building

Turn One Keyword Into 50 Outreach Drafts

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

  • 50 drafts from one keyword
  • Apollo contact discovery
  • Bulk approve before sending
Track All Client Rankings in One Place

Daily Monitoring

Track All Client Rankings in One Place

Daily rank tracking across every client workspace with full keyword history. Results scoped per client via X-Workspace-Id. Available via REST, MCP tool, and dashboard — white-label-ready.

  • Daily tracking across all clients
  • Per-keyword position history
  • White-label ready reporting
See Which Clients Appear in AI Search

AI Search Visibility

See Which Clients Appear in AI Search

Track brand citations across ChatGPT, Claude, and Perplexity for any target query using research.ai_citation.check and research.ai_citation.share_of_voice. Returns historical citation trajectory per client workspace.

  • ChatGPT, Claude, Perplexity tracking
  • Share-of-voice per AI engine
  • Historical citation trajectory

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 Automating Your Agency SEO Ops

CitationBench gives your agency one platform to research, write, publish, index, link-build, and measure across every client.

Start Free