CitationBench's agency SEO API unifies research, content production, link-building, and rank tracking into one platform. Manage your entire client portfolio without juggling fragmented tools.
# Scope all calls to a client workspace via header> X-Workspace-Id: ws_acme_co# Kick off keyword research for a new clientPOST /v1/research/keyword> { "seed": "https://acme.com", "limit": 50, "label": true }{ "keywords": 50, "labeled": true, "job_id": "job_kw_7rp4x" }# Launch search-to-outreach from one keywordPOST /v1/link-building/serp-outreach> { "keyword": "best seo platform for agencies", "workspace": "ws_acme_co" }drafts_generated: 50 · status: awaiting_approvalGeneric API tools were not built for agency scale and leave critical gaps across research, production, and distribution.
Stitching Ahrefs, Surfer, and Apollo together for each new client burns time your team cannot recover.
Fragmented tools mean keyword data, content drafts, and outreach campaigns live in separate, disconnected systems.
Standard SEO APIs have no visibility into whether your clients appear in ChatGPT, Claude, or Perplexity results.
The fix
CitationBench provides a single REST API and hosted MCP server covering research, content generation, publishing, indexing, link-building, and AI citation tracking. Multi-workspace architecture scopes every call to the right client via X-Workspace-Id.
Five purpose-built capabilities that cover the full SEO ops lifecycle across your entire client portfolio from a single API.
Agency Architecture
Manage every client brand under a single master API key. All calls scoped via the X-Workspace-Id header, with full isolation for keywords, content, campaigns, and link-building settings per workspace.
Research
POST /v1/research/keyword discovers, clusters, and labels keyword sets seeded from any client URL. Results are labeled on intent and relevance axes and persisted for production and distribution workflows downstream.
Link Building
A single POST /v1/link-building/serp-outreach call turns any keyword into a SERP scrape, Apollo contact discovery, and 50 personalized Instantly email drafts ready for human approval before any message is sent.
GEO Monitoring
Track whether each client is cited in ChatGPT, Claude, and Perplexity for target queries via research.ai_citation.check. Returns share-of-voice per engine with historical trajectory for client reporting.
Client Safety
Any agent workflow can pause and emit awaiting_approval before taking a client-facing action. Account managers review and approve via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged.
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 your agency one API for research, content, indexing, link-building, and AI citation tracking across every client.
Start Free