Agency Rank Tracking Across Every Client Workspace
CitationBench delivers daily agency rank tracking plus AI citation monitoring in one platform. One API key, unlimited client workspaces, no stitching tools together.
Generic Rank Trackers Break at Agency Scale
Running rank tracking across 10 to 100 client brands exposes every limitation of tools built for single-site users.
Siloed Data Across Client Accounts
AgencyAnalytics and similar tools force per-client logins, making unified portfolio-level rank reporting time-consuming and error-prone.
No Daily Cadence at Portfolio Scale
Weekly crawl windows miss ranking volatility that clients notice first, leaving your team defending data gaps on calls.
Rank Data Without AI Search Coverage
Traditional trackers show Google positions but miss whether clients appear in ChatGPT, Claude, or Perplexity results entirely.
The fix
One Platform. Daily Rank Tracking Across Every Client.
CitationBench tracks keyword rankings daily across all client workspaces via a single API key. Each workspace is isolated by X-Workspace-Id. Traditional rank data and AI citation share-of-voice ship together in one unified platform.
Everything Agencies Need to Track and Report Rankings
From daily position monitoring to AI citation tracking and link-building automation, CitationBench covers the full measurement and growth loop for agency portfolios.
Core Measurement
Daily Rank Tracking Across Client Workspaces
Track keyword rankings daily across every client brand. Results are scoped per client via the X-Workspace-Id header. Pull bulk rank data across your entire portfolio from a single API key.
- Daily position updates per client
- Bulk rank pulls across workspaces
- REST, MCP, and dashboard access
Agency Architecture
One API Key for All Client Brands
Manage every client workspace under a single master API key. Call any endpoint with the X-Workspace-Id header to scope keywords, rank history, campaigns, and content to the right client account.
- X-Workspace-Id client isolation
- Workspace-level settings per client
- Bulk actions across all workspaces
GEO Measurement
Track AI Search Citations Alongside Ranks
While you track Google positions, research.ai_citation.share_of_voice tracks whether each client brand is cited in ChatGPT, Claude, and Perplexity. One platform closes the SEO and GEO measurement gap.
- ChatGPT, Claude, Perplexity tracking
- Share-of-voice per AI engine
- Historical citation trajectory
Agency Controls
Human Approval Gates on Automated Actions
Agents pause at any step and emit awaiting_approval. Reviewers approve or reject via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is auditable, giving you client-safe controls on automated workflows.
- Pause before publishing or outreach
- Logged approval decisions per client
- Resume agent from last checkpoint
Link Building
Turn Client Rankings Into Link Outreach Campaigns
A single POST /v1/link-building/serp-outreach call scrapes the SERP for a target keyword, finds contacts via Apollo, and generates 50 personalized outreach drafts via Instantly. Bulk-approve before any email sends.
- One keyword to 50 email drafts
- Apollo-powered contact discovery
- Instantly.ai email integration
How it works
From sign-up to first call in five minutes.
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.
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.
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.
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 Agency Rank Tracking Across Every Client
Daily rank tracking and AI citation monitoring across all your client workspaces in one platform.
Book a Demo