CitationBench

Enterprise SEO Platform with API for Full Stack Ops

CitationBench is an enterprise SEO platform with a unified REST API and hosted MCP server covering the entire workflow — research, write, publish, index, link-build, and measure — in one developer-grade product.

Talk to SalesRead the docs
CitationBench API · Enterprise SEO
# Discover and label keywords for a client workspacePOST /v1/research/keyword> { "seed": "enterprise seo platform", "limit": 50, "label": true }{ "keywords": [{ "kw": "enterprise seo api", "intent": "COMMERCIAL",    "relevance": "core", "volume": 1200 }, ...] }# Trigger full brand bootstrap agent for a new clientPOST /v1/agent/invoke> { "agent": "brand-bootstrap", "input": { "url": "https://client.com" },>   "headers": { "X-Workspace-Id": "ws_client_42" } }job_id: job_9zt4r · status: running · awaiting_approval: false

One API Is Not Enough Anymore

Enterprise SEO teams lose hours daily stitching together tools that were never designed to talk to each other.

Fragmented tools kill velocity

Ahrefs, Surfer, Apollo, and AgencyAnalytics each have separate APIs, auth systems, and data models that require constant maintenance.

AI search is a blind spot

Every major enterprise SEO platform tracks traditional rankings but has no view into ChatGPT, Claude, or Perplexity citations.

Agents fail without durable jobs

Fire-and-forget LLM calls break under load, lose state on restart, and offer no audit trail for compliance-sensitive teams.

The fix

One API. Every SEO workflow. Zero integration debt.

CitationBench replaces your fragmented toolchain with a single REST API and hosted MCP server covering research, content production, publishing, indexing, link-building, and AI citation tracking — all scoped per client workspace.

Every Workflow Available Through One API

Five core capability areas — from keyword research to durable agent orchestration — all accessible via REST, MCP, or TypeScript SDK.

One API Key for All Client Workspaces

Agency Architecture

One API Key for All Client Workspaces

Manage every client brand under a single master API key. Each workspace is fully isolated — keywords, content, campaigns, and settings — scoped per request via the X-Workspace-Id header. Bulk actions run across all workspaces simultaneously.

  • Single key, N workspaces
  • X-Workspace-Id scoping
  • Bulk cross-workspace actions
Invoke End to End SEO Agents via API

Agent Orchestration

Invoke End to End SEO Agents via API

POST /v1/agent/invoke runs named agents — including the brand-bootstrap agent — with structured input, real-time SSE streaming, and approval-gated pauses at any step. The agent.invoke MCP tool exposes the same capability to any LLM client.

  • Brand bootstrap in 20 minutes
  • SSE real-time streaming
  • Approval-gated pause and resume
Durable Jobs That Survive Restarts

Job Reliability

Durable Jobs That Survive Restarts

Every agent job is backed by Cyclonic workers — resumable, cancellable, and auditable. Cancel via agent.invocations.cancel, resume via agent.invocations.continue. No lost state, no silent failures, no fire-and-forget risk.

  • Survive process restarts
  • Cancel and resume any job
  • Full audit log per invocation
Track AI Citations Alongside Traditional Ranks

GEO Measurement

Track AI Citations Alongside Traditional Ranks

research.ai_citation.check queries ChatGPT, Claude, and Perplexity for target queries and returns share-of-voice, citation rank, and historical trajectory — unified alongside traditional rank tracking in one API surface.

  • ChatGPT, Claude, Perplexity
  • Share-of-voice by engine
  • Daily citation scheduling
Typed TypeScript SDK for Every Endpoint

Developer Tooling

Typed TypeScript SDK for Every Endpoint

The official @citationbench/sdk covers all REST endpoints with full TypeScript type coverage. Works independently or alongside the hosted MCP server at mcp.citationbench.com/mcp for AI agent workflows.

  • @citationbench/sdk
  • Full TypeScript type coverage
  • REST and MCP compatible

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 Building on the SEO API

One enterprise SEO platform with a unified API for research, production, indexing, link-building, and AI citation tracking.

View API Docs