CitationBench

SEO Data API for Building AI Agents and Ops Tools

CitationBench's SEO data API gives developers and agencies ~35 endpoints covering SERP analysis, competitor intelligence, AI citation tracking, and full-pipeline automation — via REST or hosted MCP server.

Talk to SalesRead the docs
CitationBench API · SEO Data
# Fetch live SERP data for any queryPOST /v1/research/serp/fetch> { "query": "best seo tools for agencies", "limit": 10 }{ "results": [{ "position": 1, "domain": "ahrefs.com", "da": 91 }, ...# Run keyword research with 2D intent x relevance labelingPOST /v1/research/keyword> { "seed": "seo data api", "limit": 50, "label": true }{ "keywords": [{ "kw": "serp api", "intent": "COMMERCIAL", "relevance": "CORE" }, ...# Or call via MCP from Claude Code / Cursor> claude mcp add citationbench --url https://mcp.citationbench.com/mcp✓ Connected · 35 tools available

Generic APIs Are Not Built for SEO

Most data APIs lack the SEO-specific depth and structure that accurate agents and analytics tools require.

SERP data without structure

General-purpose data APIs return raw HTML or shallow results with no intent labels, authority signals, or gap detection.

No AI citation visibility

Off-the-shelf SEO APIs track Google ranks but are completely blind to ChatGPT, Claude, and Perplexity citation data.

Months of integration debt

Stitching Ahrefs, Surfer, Apollo, and AgencyAnalytics into one pipeline means months of glue code before you ship anything.

The fix

One SEO Data API. Every Signal You Need.

CitationBench exposes ~35 endpoints covering keyword research, SERP analysis, competitor intelligence, AI citation tracking, content production, indexing, and link-building — callable via REST, TypeScript SDK, or hosted MCP server at mcp.citationbench.com/mcp.

Every SEO Data Endpoint in One API Surface

From keyword discovery through rank tracking and AI citation monitoring, every tool is available via REST, MCP, or the TypeScript SDK.

Live SERP Data for Any Query

SERP Data

Live SERP Data for Any Query

Fetch real-time SERP data for any query via POST /v1/research/serp/fetch. Returns ranked results, domain authority signals, and content types — structured for downstream agents and analytics pipelines.

  • Live top-result fetch
  • Domain authority signals
  • Content type classification
Keyword Research with Intent Labeling

Keyword Data

Keyword Research with Intent Labeling

POST /v1/research/keyword discovers, clusters, and labels full keyword universes from a seed URL or list. Every keyword tagged by intent and relevance — filterable via research.keyword.search for downstream content prioritization.

  • Seed-to-universe discovery
  • 2D intent x relevance labels
  • Bulk import supported
AI Citation Data Across Three Engines

GEO Data

AI Citation Data Across Three Engines

Track brand citations in ChatGPT, Claude, and Perplexity via research.ai_citation.check and research.ai_citation.share_of_voice. Returns share-of-voice per engine with historical trajectory — no other SEO data API closes this loop.

  • ChatGPT citation tracking
  • Claude and Perplexity coverage
  • Share-of-voice history
Competitor Backlinks and Keyword Overlap

Competitor Data

Competitor Backlinks and Keyword Overlap

Add competitor URLs to pull their backlink profiles and keyword universes via research.competitor.backlinks and research.competitor.keywords. Generates overlap matrices so your agent or dashboard knows exactly where the gap is.

  • Backlink profile pulls
  • Keyword overlap matrix
  • Multi-competitor comparison
Hosted MCP Server with 35 SEO Tools

Developer Access

Hosted MCP Server with 35 SEO Tools

All ~35 SEO data tools are available at mcp.citationbench.com/mcp — no self-hosting, no extra infra. Works out of the box with Claude Code, Cursor, Claude Desktop, and Windsurf via the MCP protocol.

  • No self-hosting required
  • Works with Claude Code and Cursor
  • Namespaced tool registry

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 Data API

Access ~35 SEO and GEO data endpoints via REST, TypeScript SDK, or hosted MCP server — one platform, every signal.

View MCP Docs