MCP Server for GEO Built for AI Agents
CitationBench provides a hosted MCP server for GEO and SEO with ~35 specialized tools. Connect to Claude Code, Cursor, or Windsurf and build production-grade visibility agents without months of API integration.
# Add CitationBench MCP server for GEO to Claude Code> claude mcp add citationbench --url https://mcp.citationbench.com/mcp✓ Connected · 35 tools available# Track brand citations across AI search enginesresearch.ai_citation.check> { "query": "best GEO platform for agencies", "engines": ["chatgpt","claude","perplexity"] }chatgpt · cited: ✓ rank: 2 share_of_voice: 0.38claude · cited: ✓ rank: 4 share_of_voice: 0.21perplexity · cited: ✗ rank: — share_of_voice: 0.00Generic MCP Servers Miss GEO Entirely
Most MCP servers expose generic web tools. None are built for GEO workflows or AI citation visibility.
No GEO tools in existing servers
Generic MCP servers like browser-use or Fetch have zero tools for tracking AI search citations or share of voice.
Months of integration debt
Stitching Ahrefs, Profound, and Instantly APIs into a custom agent tool layer costs months before you ship anything.
AI search results stay invisible
Traditional SEO APIs track Google ranks but return nothing when clients ask if they appear in ChatGPT or Perplexity.
The fix
One hosted MCP server. GEO and SEO covered.
CitationBench exposes ~35 production-ready MCP tools across research, production, distribution, and agent namespaces. Connect once at mcp.citationbench.com/mcp and get AI citation tracking, keyword research, rank tracking, and link-building in every agent you build.
Every GEO and SEO Tool Your Agent Needs
Five tool categories purpose-built for GEO agents: citation tracking, keyword intelligence, content production, indexing, and durable job orchestration.
MCP Infrastructure
Hosted MCP Server for GEO Agents
Production-ready server at mcp.citationbench.com/mcp with ~35 tools across research.*, produce.*, indexing.*, link_building.*, and agent.* namespaces. No self-hosting required. Works with Claude Code, Cursor, Claude Desktop, and Windsurf.
- 35 tools, zero self-hosting
- Works with Claude Code and Cursor
- Multi-workspace via X-Workspace-Id
GEO Visibility
AI Citation Tracking Across All Engines
Call research.ai_citation.check to measure brand citations in ChatGPT, Claude, and Perplexity. Returns share-of-voice per engine with historical citation trajectory. Daily query scheduling keeps your agent up to date automatically.
- ChatGPT, Claude, Perplexity coverage
- Share-of-voice with history
- Daily scheduled citation checks
Agent Orchestration
Invoke Full GEO Workflows From One Call
POST /v1/agent/invoke runs named agents with structured input, real-time SSE event streaming, and approval-gated pauses. Bootstrap a full SEO and GEO presence or run daily citation monitoring without managing step-by-step tool calls.
- SSE event streaming
- Approval-gated pause and resume
- Named agents with schema registry
Reliability
Durable Jobs That Survive Restarts
All agent jobs run on Cyclonic workers. Cancel via agent.invocations.cancel, resume via agent.invocations.continue. GEO monitoring jobs are resumable and auditable, not fire-and-forget LLM calls that silently fail.
- Survives process restarts
- Cancel and resume anytime
- Full audit log per invocation
Measurement
Daily Rank Tracking Alongside GEO Data
Track traditional keyword positions daily across all client workspaces alongside AI citation data in the same platform. Results scoped per client via X-Workspace-Id. Available via MCP tool, REST, and dashboard.
- Daily position history per keyword
- Scoped per client workspace
- Available via MCP and REST
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
Build Your GEO Agent Today
Connect the CitationBench MCP server and get ~35 GEO and SEO tools in your AI agent without months of integration work.
View MCP Docs