CitationBench is a REST API and hosted MCP server that automates the full SEO workflow — keyword research, content production, publishing, indexing, link-building, and rank tracking in one developer-grade platform.
# Run keyword research via the SEO APIPOST /v1/research/keyword> { "seed": "seo api for developers", "limit": 25, "label": true }{ "keywords": [{ "kw": "seo api", "intent": "COMMERCIAL", "relevance": "CORE" }, { "kw": "rank tracking api", "intent": "COMMERCIAL", "relevance": "ADJACENT" }] }# Trigger full brand bootstrap agentPOST /v1/agent/invoke> { "agent": "brand-bootstrap", "input": { "url": "https://acme.com" } }job_id: job_9qt4r · status: running✓ Keyword universe built (312 keywords labeled)✓ Content plan ready · awaiting_approvalStitching together six separate APIs for SEO creates integration debt that never ships.
Connecting Ahrefs, Surfer, Apollo, and Instantly separately means months of glue code before any SEO workflow runs end to end.
Generic SEO APIs cover one step — keyword research or rank tracking — forcing developers to build and maintain multiple client credentials and rate-limit handlers.
Every major SEO API is blind to ChatGPT, Claude, and Perplexity citations, leaving a growing traffic source unmeasured and unreported.
The fix
CitationBench exposes research, content production, publishing, indexing, link-building, and rank tracking through a single REST API and hosted MCP server at mcp.citationbench.com/mcp, with a TypeScript SDK and durable agent jobs that run end to end without fire-and-forget fragility.
From keyword discovery to outreach campaigns, every step of the SEO workflow is callable via REST, MCP tool, or TypeScript SDK with no self-hosting required.
Research API
POST /v1/research/keyword discovers, clusters, and labels keyword sets from a seed URL or list. Results persist for downstream production steps via research.keyword.bulk_create and search endpoints.
Agent Orchestration
POST /v1/agent/invoke runs named agents like brand-bootstrap across the full research-to-publish pipeline. Supports SSE event streaming, multi-turn continuation, and approval-gated pauses mid-workflow.
MCP Integration
A production-ready hosted MCP server at mcp.citationbench.com/mcp exposes ~35 tools across research.*, produce.*, indexing.*, and link_building.* namespaces. No self-hosting, works with Claude Code and Cursor today.
Link Building
One POST /v1/link-building/serp-outreach call scrapes a SERP, runs Apollo contact discovery, and drafts 50 personalized link-building emails via Instantly. Bulk-approve before any email sends.
Developer Tooling
The official @citationbench/sdk TypeScript package provides full type coverage across all REST endpoints. Works alongside the MCP server or independently for teams writing Node.js SEO automation scripts.
How it works
An `sk_test_*` key lands in your dashboard instantly. No demo gate — start calling real endpoints with shape-complete responses.
`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.
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.
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
Hosted at mcp.citationbench.com/mcp. Works with Claude Code, Cursor, Claude Desktop, Windsurf, and ChatGPT Apps. No self-hosting required.
Every long-running call runs on Cyclonic workers — survives restarts, cancellable, resumable, streams via SSE. Production-safe by default.
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.
Every endpoint responds in shape-complete demo mode without auth, so you can build the agent before the user signs up.
FAQ
CitationBench gives developers one REST API and hosted MCP server to automate the full SEO workflow without integration overhead.
View API Docs