CitationBench

SEO API for Building AI Powered Tools and Agents

CitationBench is a developer-grade SEO API with ~35 tools covering research, content production, publishing, indexing, link building, and AI citation tracking — all in one unified platform.

Talk to SalesRead the docs
CitationBench API · SEO Tools
# Start with keyword research via REST or MCPPOST /v1/research/keyword> { "seed": "seo api", "limit": 25, "label": true }{ "keywords": [{ "kw": "seo api integration", "intent": "COMMERCIAL",  "relevance": "core", "volume": 1400 }, ...] }# Track AI citations alongside traditional rank dataPOST /v1/research/ai-citation> { "query": "best seo api for developers", "engines": ["chatgpt","perplexity"] }chatgpt    · cited: ✓  rank: 2  share_of_voice: 0.33perplexity · cited: ✗  rank: —  share_of_voice: 0.00

Standard SEO APIs Leave Gaps

Generic SEO APIs cover keyword data and rank tracking but stop short of what modern apps and agents actually need.

No AI Search Visibility

Most SEO APIs track Google ranks but are completely blind to whether your brand appears in ChatGPT, Claude, or Perplexity.

Fragmented Tool Chains

Stitching Ahrefs, Surfer, Apollo, and Instantly together forces your team to manage multiple API keys, schemas, and rate limits.

Fire and Forget Automation

Generic automation APIs run jobs with no durability, no approval gates, and no way to recover a workflow that crashes mid-run.

The fix

One SEO API. Research to Indexing to Outreach.

CitationBench exposes the full organic visibility workflow as a single REST API and hosted MCP server. Call endpoints for keyword research, content generation, multi-platform publishing, AI citation tracking, and link-building outreach — with durable jobs and human approval gates built in.

Every SEO API Endpoint Your App Needs

From keyword discovery and content generation to indexing automation and link outreach, every workflow is accessible via REST, MCP tool, or TypeScript SDK.

Keyword Research Endpoint With 2D Labeling

Research API

Keyword Research Endpoint With 2D Labeling

Call POST /v1/research/keyword with a seed URL or term to discover, cluster, and label a full keyword universe. Results persist and flow directly into content production endpoints. Bulk import via research.keyword.bulk_create.

  • Intent and relevance labels
  • Persistent result storage
  • Bulk keyword import
AI Citation Tracking Alongside Rank Data

GEO Measurement

AI Citation Tracking Alongside Rank Data

Track brand citations across ChatGPT, Claude, and Perplexity via research.ai_citation.check. Returns share-of-voice per engine with historical trajectory — the only SEO API that closes the loop between traditional and AI search.

  • ChatGPT Claude Perplexity coverage
  • Share of voice history
  • Daily query scheduling
Hosted MCP Server With 35 SEO Tools

MCP Integration

Hosted MCP Server With 35 SEO Tools

Connect to mcp.citationbench.com/mcp from Claude Code, Cursor, or any MCP client and get ~35 namespaced SEO tools instantly. No self-hosting. Tools span research.*, produce.*, indexing.*, link_building.*, and agent.* namespaces.

  • No self-hosting required
  • Works with Claude Code Cursor
  • 35 tools across all namespaces
Agent Invoke Endpoint for End to End Workflows

Agent Orchestration

Agent Invoke Endpoint for End to End Workflows

POST /v1/agent/invoke runs named agents with structured input, real-time SSE streaming, and approval-gated pauses. Build full SEO pipelines from a single API call — from keyword research through published content and indexed URLs.

  • SSE event streaming
  • Approval gate pauses
  • Named agent registry
TypeScript SDK for Every REST Endpoint

Developer SDK

TypeScript SDK for Every REST Endpoint

Install @citationbench/sdk for full type coverage across all REST endpoints. TypeScript-first with complete type definitions. Works alongside the MCP server or independently for Node.js applications and custom integrations.

  • Full TypeScript type coverage
  • Works with MCP or standalone
  • Python SDK coming next

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 With the SEO API

CitationBench gives developers and agencies one API for keyword research, content production, AI citation tracking, and link-building automation.

View API Docs