Rank Tracking API for Agencies Managing Every Client
CitationBench gives agencies a developer-grade rank tracking API with daily SERP updates and AI citation monitoring across every client workspace from one API key.
One Tool Never Fits Every Client
Agencies juggling multiple clients need rank tracking that scales without breaking reporting workflows or margins.
Client count breaks your tools
AgencyAnalytics and similar dashboards charge per client, making margin destruction inevitable as your portfolio grows.
SERP data misses AI search
Traditional rank trackers show Google positions but leave clients blind to ChatGPT, Claude, and Perplexity citations.
Manual reporting kills capacity
Pulling rank data client by client and pasting into reports consumes hours your team could spend on strategy.
The fix
One API Key. Every Client. Daily Rank Data.
CitationBench delivers daily rank tracking across all client workspaces via a single master API key. Scope every call by client with the X-Workspace-Id header, pull bulk rank data, and surface both SERP positions and AI citation share-of-voice in one unified response.
Built for Agencies Running Dozens of Clients
Five purpose-built capabilities that automate rank monitoring, competitor research, and reporting across your entire client portfolio.
Core Tracking
Daily Rank Tracking Across All Client Workspaces
Pull per-keyword rank history for every client via the REST API or MCP tool, all scoped by X-Workspace-Id. Bulk rank pulls across all workspaces eliminate per-client polling loops.
- Daily SERP position updates
- Bulk cross-workspace pulls
- Full keyword history
Agency Architecture
Single API Key for Every Client Brand
One master API key manages N client workspaces. Workspace-level isolation keeps keywords, campaigns, and settings separate per client while giving your team a unified API surface.
- X-Workspace-Id scoping
- White-label-ready isolation
- Bulk actions across clients
AI Visibility
Track AI Citations Alongside SERP Ranks
Monitor brand citations in ChatGPT, Claude, and Perplexity for each client's target queries via research.ai_citation.check. Returns share-of-voice history alongside traditional rank data.
- ChatGPT, Claude, Perplexity
- Share-of-voice trending
- Daily scheduled queries
Competitive Research
Competitor Backlinks and Keyword Overlap Per Client
Add competitor URLs per client workspace to pull backlinks and keyword universes via research.competitor.backlinks and research.competitor.overlap. Generates keyword overlap matrices for gap identification.
- Per-workspace competitor sets
- Backlink profile pulls
- Keyword overlap matrices
Client Governance
Approval Gates Before Any Report Goes Out
Agents pause at configurable checkpoints and emit awaiting_approval. Reviewers approve or reject via the dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged and auditable.
- Dashboard approval UI
- Auditable decision log
- Resume exactly where paused
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 Tracking Every Client Rank Today
One API key, daily SERP and AI citation data, unlimited client workspaces — built for agencies that need reliable rank tracking at scale.
Start Free