API for Landing Page Generation at Agency Scale
The CitationBench API for landing page generation creates thousands of on-brand pages programmatically, with reusable content refiners that enforce brand voice across every client workspace.
Manual Builds Cannot Scale to Clients
Agencies managing dozens of clients cannot hand-build landing pages without sacrificing speed, consistency, or brand fidelity.
Brand voice breaks at scale
Without reusable style rules, every new client page drifts from approved tone and messaging guidelines.
Pages sit un-indexed for weeks
Manual GSC submissions get skipped or delayed, leaving new landing pages invisible to search engines after publish.
One build pipeline per client
Most landing page tools require separate setups per client, making a portfolio of 20 brands a maintenance nightmare.
The fix
One API. Thousands of Pages. Every Brand Consistent.
CitationBench exposes programmatic landing page generation via `produce.landing_page.create`, scales from 1 to 10,000 pages, enforces brand voice through reusable content refiners, and auto-indexes every page on publish via GSC and IndexNow.
Everything the Landing Page Generation API Delivers
Five purpose-built capabilities that take agencies from keyword input to indexed, on-brand landing pages across every client workspace.
Core Production
Programmatic Landing Pages at Any Scale
Generate landing pages from keyword and pillar schema via `produce.landing_page.create`. Pillar schemas are defined once and reused across clients. Scale from a single page to thousands without rebuilding the pipeline.
- 1 to 10,000 pages
- Reusable pillar schemas
- Section-level regeneration
Brand Consistency
Enforce Client Brand Voice Across Pages
Reusable refiners apply brand voice rules, CTA insertions, and competitor removal automatically after generation via `produce.refine.*`. Configure once per client workspace and every page inherits the same rules.
- Per-workspace refiner configs
- CTA and FAQ injection
- Competitor mention removal
Instant Discoverability
Auto-Index Every Landing Page on Publish
Every `produce.publish` call automatically fires Google Search Console URL submission and IndexNow in parallel. No page goes live and sits un-indexed because a manual step was skipped.
- GSC submission on publish
- IndexNow simultaneous fire
- No manual indexing step
Agency Architecture
Manage All Client Pages From One Key
One master API key manages N client workspaces. Scope every landing page creation and publish call per client via the `X-Workspace-Id` header. Content, settings, and refiners stay isolated per brand.
- Single master API key
- X-Workspace-Id scoping
- Bulk actions across clients
Human Review
Gate Publish Steps Awaiting Client Approval
Any page generation pipeline can pause and emit `awaiting_approval` before publishing. Clients or account managers review via dashboard or `POST /v1/agent/invocations/{id}/approve`. Every decision is logged.
- Pause at any generation step
- Approve via dashboard or API
- Full audit log per decision
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 Generating Landing Pages via API
Give your agency a single API that generates, refines, publishes, and indexes thousands of on-brand landing pages across every client.
Start Free