For AI agents · MCP

Your SEO data inside the agents you already use

The Seonix MCP server lets the AI agent you already work with read your Site Health report and fix plan, pull Search Console queries, browse keyword clusters and articles, and score a draft before it goes live. Ask in plain language; the agent calls Seonix.

Any agent

>Connect Seonix to this project over MCP: https://seonix.ai/mcp.md

Paste this into Claude Code, Cursor, Codex or any agent with MCP support. It reads the manifest, shows you a link to confirm once and wires the server in.

No keys to copy: your agent shows a link, you click Connect once. Read-only, listed in your account, revocable any time. Part of every paid plan. app.seonix.ai/account/agents

See what the agent can do

Example session · Claude Code

Fix everything Seonix found on my site and tell me what changed.

get_site_healthSite Health 61 · 43 open problems
get_fix_plan14 items · 3 site-wide, 11 page-level
analyze_seorewritten page scores 84/100

Done: canonical tags, 9 meta descriptions, alt text on 31 images and the sitemap path in robots.txt. Start a rescan in Seonix and I will confirm what cleared.

After rescan: 61 → 88

Claude Code

Anthropic

One command, headers supported.

Cursor

Anysphere

Entry in ~/.cursor/mcp.json.

Codex

OpenAI

MCP server in the Codex config.

Copilot

GitHub

VS Code reads .mcp.json.

Windsurf

Same mcpServers entry.

Works with any client that speaks the Model Context Protocol over HTTP with a bearer header. Claude.ai and ChatGPT connectors need sign-in with OAuth, which is on the way.

What it is

The product you pay for, reachable from a chat

MCP (Model Context Protocol) is the open standard AI agents use to call outside tools. Seonix publishes its own server: every read your dashboard can do — the Site Health report, the issue list with evidence, Search Console queries and pages, keyword clusters, articles, scores — becomes a tool the agent calls with your permission.

The agent does the thinking with its own model; Seonix supplies the facts and the scoring. No AI credits are spent on reads, and the agent never sees another account's data.

MCP URLhttps://api.seonix.ai/mcp·Read the agent manifest

Seonix Site Health dashboard: an overall score of 91 out of 100, SEO, technical, speed and AI search scores, and the list of issues to fix — Site Health checks every page for SEO, technical, speed and AI-search issues and marks which ones Seonix fixes for you.

What your agent can do

Six things to ask it today

Read Site Health and get a fix plan

The score by pillar, every open problem with the offending tag or redirect chain, and an ordered plan a coding agent can apply file by file.

Pull Search Console insights

Top queries and pages, the queries one page ranks for, striking-distance keywords at positions 4–20, indexing coverage and a 28-day trend.

Browse keywords and clusters

Researched keywords with volume and Search Console numbers, topic clusters with intent and page type, and the competitor insights behind each.

Score a draft before publishing

Any title, body and meta the agent wrote goes through the same SEO, readability and AI-answer checks the dashboard uses. Iterate until it passes.

Read articles and the calendar

What was published and when, each article's score and keyphrase, where it is live, and the slots planned for the month.

Follow Seonix playbooks

Ten step-by-step procedures the agent can run: promote the site, work through a page, fix issues in code, map keywords, write for a cluster, report monthly.

Try these

Three prompts to start with

Copy one into your agent once Seonix is connected. Each one maps to a playbook the server ships.

>Use Seonix: get the fix plan for my site, apply every page-level item in this repo, then tell me what to rescan.

Prompts are English on purpose: agents follow English instructions most reliably. Ask in your language — the agent answers in it.

Tool reference

36 read tools, grouped the way the dashboard is

Every tool is read-only and marked as such for the client, so agents do not ask for confirmation before reading. Each returns compact JSON with a hint on what to call next.

01Account and project6

get_accountProjects, plans, quotas, whether the MCP is available
list_projectsId, slug, name and site URL of each project
get_projectAutopilot mode, channels, Search Console status, links
get_site_dnaBrand, audience, tone and writing instructions as a prompt block
get_plan_statusPlan, permissions and the upgrade link
get_seo_progressSEO Progress level and what the next one needs

02Site Health7

get_site_healthScore, pillars, counts, top open problems, last scan
list_issuesIssue threads by status, code or URL, paginated
get_issueOne issue with the captured evidence and the remediation profile
get_fix_planOrdered, implementable plan with URLs and target markup
get_remediation_profileWhy a code matters, bad vs good example, steps
list_scansRecent scans with status and counts
get_scan_statusProgress of one scan

03Search Console and GA49

gsc_statusConnection, property, last published day
gsc_top_queriesTop queries in the window
gsc_top_pagesTop landing pages in the window
gsc_page_queriesQueries one page ranks for
gsc_opportunitiesStriking-distance keywords by estimated gain
gsc_timeseriesDaily clicks, impressions and position, 7–90 days
gsc_coverageIndexed and not-indexed pages with verdicts
gsc_impactSeonix's own impact estimate
ga4_overviewGA4 totals and top pages when connected

04Keywords and calendar4

list_keyword_candidatesResearched keywords with volume and GSC numbers
list_clustersTopic clusters with intent, priority and winnability
get_clusterMembers, covering pages, SERP snapshot and insights
get_calendarSlots for a month: kind, source, status

05Articles and results8

list_articlesArticles with scores and publish dates
get_articleOne article with meta, takeaways, publications, HTML on request
analyze_seoScore any draft: SEO, readability, AI-answer readiness
score_articleRe-score an existing article
list_channelsConnected publishing channels
get_ai_visibilityLatest ChatGPT-mention snapshot
get_resultsPer-article clicks and positions vs the previous period
get_blog_integration_guideHow to connect a custom-built blog

06Playbooks2

list_playbooksThe ten procedures with a one-line summary
get_playbookOne procedure in full, also served as an MCP prompt

Plans

Included in every paid plan

There is no separate MCP subscription: the server is another way into the project you already pay for, with the same limits as the dashboard.

On the Free plan nothing works: every call answers plan_required with the upgrade link. Writes (applying fixes, publishing) arrive in the next phase.

	Free	Starter and above
Connect an agent
Site Health, issues and fix plan
Search Console and GA4 data
Keywords, clusters, articles, calendar
Draft scoring with analyze_seo
Playbooks and guides
Tool calls per agent	—	600 per hour

Safety

Built for agents that have shell access

Read-only today

Every tool reads. Nothing on your site, in Seonix or in your repository changes unless the agent you run changes it.

Your data only

A key belongs to one account; every call re-checks that the project is yours and on a paid plan.

Untrusted content is labelled

Text crawled from your pages or taken from search results is marked as data, and the server tells the agent never to treat it as instructions.

Access you control

Every connected agent is listed in your account with its last use and client. Disconnect it in one click. Access stops when you change your password.

Frequently asked questions

Which agents and clients work with it?

Any client that supports the Model Context Protocol over HTTP with a custom header: Claude Code, Cursor, Codex, Windsurf, VS Code and others. Claude.ai and ChatGPT connectors require OAuth sign-in instead of a key; that is in progress.

Does it spend my AI credits?

No. The tools return data and deterministic scoring; the thinking happens in the agent you run. Seonix spends AI only when you use its own generation features, which the MCP does not expose yet.

Is it included in my plan?

Yes, in every paid plan, with no extra charge. On the Free plan nothing works: the agent gets plan_required and the upgrade link.

How does the agent get access?

It asks Seonix for a connect link, you open it signed in and click Connect. The agent receives its own key and stores it in its config; you never copy one. A client that cannot run requests can still use a key from Account → AI agents & MCP.

I have several projects. Which one does the agent use?

Pass the project id or slug, or connect with the per-project address /mcp/p/<project id> so every call is scoped to one site. With a single project nothing extra is needed.

Can the agent apply the fixes?

In your own code, yes: get_fix_plan returns where and what to change, the coding agent edits the repository, you deploy and rescan. Fixes applied by Seonix itself through the WordPress plugin arrive in the next phase.

What happens if the agent loops?

Each connected agent has a budget of 600 tool calls per hour. Past that the server answers with a clear error and a retry time instead of silently failing.

Can the agent connect my custom-built blog too?

Yes. The server serves the same integration guide as seonix.ai/SKILL.md, so a coding agent can build the publishing endpoints, test them and connect the channel from one session.

Connect your site, then connect your agent

Start with the free analysis. Once your project is on a paid plan, paste one line into your agent and it sees everything Seonix knows about the site.

Analyze my site free

Connect an agent in the dashboard API docs