DocsTutorials
How to do SEO with Claude and other AI agents
How to do SEO with an AI agent: hand keyword research and rank tracking to Claude, Cursor or Codex over MCP, with a spending cap on every call.
- Model Context Protocol
- Claude
- ChatGPT
- Claude Code
- Cursor
- Codex
- Gemini CLI
Everything in the app is also available to AI agents through OpenSEO's MCP server: research, saving, trackers, audits, AI visibility and local rank tracking. You ask in plain language; the agent picks the tools, checks prices and keeps under the ceiling you set.
Connect an AI agent over MCP
Create an API key under Settings, then paste the setup prompt from Settings into your agent: it connects itself. For the skills, the Claude Code plugin and the config for each client, see Connect your agent. The skills are the quickest start: ask your agent to run the seo-coach skill.
Spending limits for AI agents
Before the examples, the rules every OpenSEO tool follows:
- Tools that spend take
dry_run, which returns the price and spends nothing, andmax_cost_usd, a ceiling you agree with the agent. A call whose price could be higher is refused before anything is spent. - Background runs (
run_rank_check,run_ai_visibility,run_geo_grid) require a ceiling. - Cached results are free, so asking the agent to look again at something from this week costs nothing.
- Your monthly spending limit applies to agents too. It is the backstop if you give an agent a broad task; set one under Settings before you do.
Three AI SEO workflows
Research and save keywords
Using OpenSEO, find keyword ideas for "emergency plumber" in my project.
Keep it under $0.20. Save the 20 with the highest volume and difficulty
under 40, tagged "q4".list_projects
The agent finds your project. With only one project, it can skip this.
keyword_ideas with dry_run
It checks the price of 150 ideas (about $0.08) against your $0.20.
keyword_ideas with max_cost_usd: 0.20
It runs the lookup with your ceiling and filters the results.
save_keywords
It saves the 20 keywords with their figures and the tag. Saving is free.
Set up tracking, with prices first
Create a weekly rank tracker for acme.com in Austin, Texas, on mobile,
top 20, with the keywords tagged "q4". Tell me what one check and one
month will cost before running anything.The agent uses search_locations to find Austin's location code (free), list_saved_keywords with the tag, and create_rank_tracker, which spends nothing. list_rank_trackers then gives the price range of one check, and the agent multiplies it by about 4.35 for a weekly month. It runs run_rank_check only when you agree, with that range as its ceiling, and reads the outcome with get_rank_results.
Give the agent memory of your project
Read the project context. Then add our goal (more booked jobs in north
Austin), our two main competitors (globex.com, initech.com) and the
pages we care about most, and save it back.Each project has free-form context notes that any agent can read with get_project and replace with update_project_context. Keep your goals, audience, competitors and key pages there, and every agent session starts from the same understanding.
More SEO tasks for your agent
| Ask | Tools the agent uses |
|---|---|
| "Who are my organic competitors, and which keywords does the top one have that I don't? Under $0.30." | competitors_domain, keyword_gap |
| "Audit acme.com, then summarise the critical issues with the URLs to fix." | start_site_audit, list_site_audits, get_site_audit, get_audit_issues |
| "Run Lighthouse on our pricing page on mobile and list the three biggest savings." | lighthouse |
| "Ask ChatGPT, Claude and Perplexity which plumbing software they recommend and tell me who gets cited." | ai_compare |
| "How much have we spent on OpenSEO this month, and what is left on YepAPI?" | get_usage, get_balance (both free) |
The full list of tools and what each one costs is in MCP tools.