Programmatic SEO Platform for Agencies at Scale
CitationBench is the programmatic SEO platform that automates the full workflow — research, write, publish, index, link-build, and measure — across every client brand your team manages.
Too Many Tools. Too Little Output.
Fragmented SEO stacks slow agencies down and leave entire workflow gaps no single tool closes.
Onboarding New Clients Takes Weeks
Setting up keywords, content briefs, and CMS configs across six separate tools burns days your team does not have.
AI Search Leaves You Blind
Your current stack tracks Google ranks but cannot tell you if clients appear in ChatGPT, Claude, or Perplexity results.
Content Scales. Consistency Does Not.
Running programmatic pages across 20 client brands means brand voice drift and quality gaps that are impossible to audit manually.
The fix
One Platform. Every SEO Op. Done.
CitationBench composes research, programmatic content generation, multi-platform publishing, auto-indexing, link building, and AI citation tracking into agentic workflows. Bootstrap a new client brand in 20 minutes with one agent call.
Every Layer of Programmatic SEO in One Platform
Five tightly integrated capabilities that take agencies from keyword discovery through published, indexed, and ranked pages across every client workspace.
Programmatic Content
Generate Landing Pages at Programmatic Scale
Create optimized landing pages programmatically via `produce.landing_page.create`. Define a pillar schema once and reuse it across every client. Scales from a single page to 10,000 without rebuilding your workflow.
- 1 to 10,000 pages
- Keyword plus pillar schema input
- Section-level regeneration supported
Keyword Intelligence
Label Keywords by Intent and Relevance
CitationBench applies an industry-first 2D taxonomy — intent (informational, commercial, transactional, navigational) crossed with relevance — to every keyword via `research.keyword.relabel`. Prioritize the right keywords before writing a single page.
- 2D intent x relevance taxonomy
- Bulk relabeling at scale
- Filter before content production
Brand Consistency
Enforce Brand Voice Across All Client Content
Reusable refiners via `produce.refine.*` apply brand voice rules, competitor removal, CTA insertion, and FAQ injection automatically after generation. Set them up once and every client workspace inherits consistent output quality.
- Configure once per account
- Auto-apply across workspaces
- CTA insertion and FAQ injection
Indexing Automation
Index Every Published Page Automatically
Every `produce.publish` call automatically fires a Google Search Console URL submission and an IndexNow ping across Bing and other compatible engines. No page goes unindexed and no manual step is required.
- GSC submission on every publish
- IndexNow fires simultaneously
- No manual indexing steps
Agency Architecture
Manage All Client Brands from One Account
One master API key manages N client workspaces. Every keyword list, content set, campaign, and rank history is scoped per client via the `X-Workspace-Id` header. White-label-ready and built for agencies running 10 to 100 brands.
- Single master API key
- Per-client workspace isolation
- Bulk actions across all brands
How it works
From sign-up to first call in five minutes.
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.
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.
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.
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 Programmatic SEO at Scale
CitationBench gives agencies one platform to research, generate, publish, index, and measure SEO across every client brand.
Book a Demo