CitationBench

AI Agents for SEO Built for Agencies

CitationBench uses AI agents for SEO to automate end-to-end workflows — from keyword research to link building — so a small team can manage an entire client portfolio.

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_9rz4m · status: running# Streaming events via SSE✓ ICP profiles generated (3 segments)✓ Keyword universe built (312 keywords labeled)✓ Content plan ready · awaiting_approval✓ Outreach drafts queued (50 drafts)

One Team Cannot Scale Without Agents

Running SEO ops across dozens of clients with manual tools means slower onboarding, inconsistent output, and missed opportunities.

Onboarding Weeks Behind Schedule

Configuring research, content, and outreach manually for each new client consumes days your team does not have.

Tools Scattered Across Six Platforms

Ahrefs, Surfer, Apollo, Instantly, and AgencyAnalytics were never built to work together — your team pays the integration tax.

No Visibility Into AI Search Results

Clients ask whether they appear in ChatGPT or Perplexity and your current stack has no answer.

The fix

One Platform. Every SEO Workflow Automated.

CitationBench composes research, content production, publishing, indexing, link building, and AI citation tracking into durable agentic workflows — with human approval gates so your team stays in control across every client workspace.

Every Tool Your SEO Agents Need

Five purpose-built capabilities that compose into end-to-end agentic workflows across your entire client portfolio.

Run End to End SEO Agents

Agentic Workflows

Run End to End SEO Agents

Invoke any named agent via POST /v1/agent/invoke with structured input. Agents compose research, production, and distribution tools into a single durable job — pausing for human sign-off when needed.

  • Brand bootstrap in 20 minutes
  • Approval gates at every step
  • SSE streaming for live monitoring
Approval Gates for Every Client Action

Human Control

Approval Gates for Every Client Action

Agents emit awaiting_approval at configurable checkpoints. Reviewers approve or reject via the dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged and auditable — critical when acting on behalf of clients.

  • Pause at any agent step
  • Approve via dashboard or API
  • Full audit log per decision
One API Key for All Client Brands

Agency Architecture

One API Key for All Client Brands

A single master API key manages N client workspaces. Every call is scoped by X-Workspace-Id header, isolating keywords, content, campaigns, and link-building data per brand without separate accounts.

  • Isolated per-client workspaces
  • Bulk actions across workspaces
  • White-label ready
One Keyword to 50 Outreach Drafts

Link Building

One Keyword to 50 Outreach Drafts

POST /v1/link-building/serp-outreach turns one target keyword into a SERP scrape, Apollo-powered contact discovery, and 50 personalized email drafts via Instantly — reviewed and bulk-approved before a single message sends.

  • Apollo contact discovery built in
  • Instantly email integration
  • Bulk draft approval before send
Track AI Citations Across All Clients

GEO Monitoring

Track AI Citations Across All Clients

Monitor brand citations in ChatGPT, Claude, and Perplexity via research.ai_citation.check and research.ai_citation.share_of_voice. Daily scheduling surfaces citation trends across all client workspaces in one unified view.

  • ChatGPT, Claude, Perplexity tracked
  • Daily share-of-voice history
  • Scheduled query monitoring

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

Automate Your Agency SEO Workflows

CitationBench gives your team AI agents for SEO that handle research, content, link building, and AI citation tracking across every client brand.

Book a Demo