CitationBench

Autonomous SEO Platform That Scales Your Agency

CitationBench is an autonomous SEO platform that runs research, content production, and link-building ops across all your client brands using durable agents and a single API.

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_9mw4r · 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 · 2 active

Stitched-Together Tools Break at Scale

Running an agency on six fragmented tools means more coordination overhead and fewer client results.

Onboarding a client takes weeks

Manually setting up Ahrefs, Surfer, and Apollo for each new client burns days before any work ships.

No visibility into AI search

Every SEO tool in your stack is blind to ChatGPT and Perplexity citations — your clients are asking.

Agents fail without oversight

Fire-and-forget LLM workflows break silently midway, with no resume, no audit trail, and no approval gates.

The fix

One Platform. Every SEO Op. Fully Autonomous.

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

Built for Agencies That Run on Automation

Every feature in the platform is composable into autonomous workflows across research, content, distribution, and link-building ops.

Autonomous Workflows Across Every SEO Op

Agentic Ops

Autonomous Workflows Across Every SEO Op

Trigger any named agent via POST /v1/agent/invoke with structured input. Supports SSE streaming, multi-turn continuation, and approval-gated pauses — so jobs are auditable, not fire-and-forget.

  • Brand bootstrap in 20 minutes
  • Real-time SSE event streaming
  • Approval-gated agent pauses
One API Key for All Client Brands

Agency Architecture

One API Key for All Client Brands

Manage every client workspace under a single master API key. Scope all calls per client via X-Workspace-Id — full isolation for keywords, campaigns, content, and rank data with unified oversight.

  • Single key manages N clients
  • Per-workspace data isolation
  • Bulk actions across workspaces
Track Client Citations in AI Search Engines

GEO Monitoring

Track Client Citations in AI Search Engines

Monitor brand mentions in ChatGPT, Claude, and Perplexity daily via research.ai_citation.check. Returns share-of-voice scores and historical citation trajectory — the reporting layer every client is now asking for.

  • ChatGPT, Claude, Perplexity coverage
  • Share-of-voice scoring
  • Historical citation trajectory
One Keyword to 50 Outreach Drafts

Link Building

One Keyword to 50 Outreach Drafts

POST /v1/link-building/serp-outreach turns a single keyword into a SERP scrape, Apollo contact discovery, and 50 personalized email drafts via Instantly — all in one call. Bulk-approve before any email sends.

  • 50 drafts from one keyword
  • Apollo-powered contact discovery
  • Bulk-approve before sending
Durable Jobs That Survive Restarts

Reliability

Durable Jobs That Survive Restarts

All agent jobs run on Cyclonic workers — fully durable, resumable, and cancellable. Cancel via agent.invocations.cancel, resume via agent.invocations.continue. No silent failures in production automation.

  • Survives server restarts
  • Resumable and cancellable jobs
  • Full invocation audit log

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

Run Your Agency on Autonomous SEO

CitationBench automates the full SEO lifecycle across every client brand from research and content to link-building and AI citation monitoring.

Book a Demo