SEO Agent
Track rankings, audit SERPs, and research keywords, competitors, and backlinks as live records — inside your assistant.
Using ChatGPT, Claude Code or another client? See the setup steps
Track rankings, audit live and AI SERPs, and research keywords, competitors and backlinks from Claude or Codex — no SEO-suite seat.
A live SEO brief: positions, SERP features, competitor gaps, and backlink evidence.
- Live organic and AI SERP positions for a keyword set
- Competitor domains and rich SERP features per query
- Keyword and backlink gap analysis vs named competitors
- Cited source records for every position and link claim
Who runs this Agent
- SEO and growth teams that want rank data in an agent, not a dashboard
- Agencies running keyword and competitor research across many clients
- Founders auditing organic visibility before and after a launch
Paste this into Claude or Codex
The prompt is editable. Replace the brand, market, competitors, or location, then let the assistant call UnifAPI MCP when it needs live public data.
Track these keywords for example.com in the US market: "unified api", "public data api", "mcp server". Return our organic and AI-overview positions, the competing domains, and the SERP features each query triggers. Then find 10 keyword gaps where competitor.com ranks and we don't, with evidence.
From public records to a decision brief
Give the agent a keyword set and a domain
Start from a list of queries, a target domain, and a market or location — no standing rank-tracking project required.
Fetch live SERP and link records
UnifAPI returns ranked elements, target visibility, competitor domains, SERP features, backlinks, and referring domains through one MCP or HTTP surface.
Report what moved and where the gaps are
The agent summarizes positions, highlights gains and losses, ranks the strongest links, and cites the SERP evidence behind each claim.
The concrete tasks SEO Agent runs
A Skill is one concrete capability — a run-prompt the Agent executes. Open a Skill for its detailed workflow, expected output, and FAQ.
SEO audit
EnhancedAudit crawlability, on-page, and content against live SERP and ranking evidence — not a static checklist.
SEO fixes
EnhancedConvert live SEO audit evidence into prioritized fixes, owners, and acceptance checks.
Keyword research
EnhancedTurn a seed list into ranked keyword opportunities and competitor gaps from live SERP and volume data.
Schema
AdviceChoose and implement the right schema.org types for a page, with valid JSON-LD the assistant can write.
Public-data tools this Agent calls
Agents are the workflow layer. The same live APIs are callable directly for product code, debugging, and custom agent flows.
Learn how this Agent works
SEO Agent live rank audits
How the SEO Agent turns SERP, keyword, backlink, and Browser records into a cited SEO brief.
Read guideSEO, GEO, and Browser as one visibility stack
A cookbook for combining classic rank, AI-answer visibility, and rendered-page evidence.
Read guideBrowser API for agent web reading
Why rendered Markdown, HTML, screenshots, and links matter in real SEO audits.
Read guideQuestions about the SEO Agent
Scope, billing, public-data boundaries, and how this Agent runs inside your assistant.
For agent-run checks, often yes: you get the underlying SERP, keyword, and backlink records on demand without a per-seat dashboard. For a standing team workspace with crawls and projects, a suite still has a place — the SEO Agent is the on-demand, scriptable layer.
No. In v1 the agent only reads public SERP and link data. It can describe on-page or technical fixes, but you or your own tools make the changes — UnifAPI never touches your site or Search Console.
Public-data reads are $0.001 per record with per-operation minimums generated from the OpenAPI contract. You reuse the Claude or Codex plan you already pay for; there is no separate LLM API key for the workflow.