Connect Claude Code to CitationBench's hosted MCP server and get ~35 SEO and GEO tools callable instantly from your agent environment. No self-hosting required.
# Add CitationBench to Claude Code in one command> claude mcp add citationbench --url https://mcp.citationbench.com/mcp✓ Connected · 35 tools available# Run keyword research directly from your agentresearch.keyword.research> { "seed": "claude code seo", "limit": 20, "label": true }{ "keywords": [{ "kw": "claude code seo agent", "intent": "PRODUCT", "relevance": "core", "volume": 880 }, ...] }# Invoke a full brand bootstrap agentagent.invoke> { "agent": "brand-bootstrap", "input": { "url": "https://acme.com" } }job_id: job_4mw9z · status: running · awaiting_approvalDevelopers using Claude Code for SEO hit the same walls: fragmented APIs, brittle integrations, and no unified tool layer.
Wiring Ahrefs, Surfer, and Apollo into a Claude Code agent means months of API keys, wrappers, and maintenance before a single keyword ships.
Most SEO APIs are not designed for agentic use. You get rate-limited, undocumented endpoints with no MCP support and no durable job system.
LLM agent calls with no approval gates or resumable jobs fail silently when tasks run long or require human sign-off mid-workflow.
The fix
CitationBench's hosted MCP server at mcp.citationbench.com/mcp exposes ~35 SEO and GEO tools across research, production, distribution, and agent namespaces. Connect once from Claude Code and run keyword research, content generation, rank tracking, and link-building campaigns without writing a single integration.
Five capabilities covering the full organic visibility workflow, all callable as MCP tools from Claude Code or any MCP-compatible client.
MCP Layer
Production-ready server at mcp.citationbench.com/mcp with ~35 tools across research.*, produce.*, indexing.*, link_building.*, and agent.* namespaces. No self-hosting. Works with Claude Code, Cursor, and Windsurf.
Research
Call research.keyword.research from Claude Code to discover, cluster, and label keyword sets from any seed. Results persist for downstream production steps and bulk import via research.keyword.bulk_create.
Agents
POST /v1/agent/invoke or call agent.invoke from Claude Code to run named agents like brand-bootstrap end-to-end. Supports real-time SSE streaming and multi-turn continuation across complex SEO workflows.
Reliability
All CitationBench agent jobs run on Cyclonic workers. Jobs are resumable and cancellable via agent.invocations.cancel and agent.invocations.continue. Not fire-and-forget LLM calls.
Control
Any agent step can emit awaiting_approval, pausing the job until a human approves via dashboard or POST /v1/agent/invocations/{id}/approve. Every decision is logged. Agents resume exactly where they stopped.
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
Add the CitationBench MCP server to Claude Code and start running keyword research, content agents, and rank tracking in minutes.
View MCP Docs