Claude
- Open Add custom connector ↗
- Name it Relvato Security Monitoring and paste the URL
- Click Add, then sign in to your account
https://security.relvato.com/api/mcp
WordPress security monitoring
Relvato Security Monitoring watches your WordPress sites for the things that turn into a breach. Through the Relvato WordPress plugin it reads the site from inside: plugins, themes and WordPress core with known vulnerabilities (most urgent when a flaw is being exploited right now), core, plugin and theme files that changed when nothing should have, admin accounts and sign-ins you didn't expect, and stale backups. From the outside it looks for signs of a hack, such as spam pages and redirects served only to Google, scripts loaded from places they shouldn't be, and sensitive files left public, like backups, .env and config files or leaked keys. Those outside checks work on any website, WordPress or not. Monitors run on a schedule and again every time the site changes.
This app brings your Relvato account's security monitoring into your AI. Sign in once, then ask in plain words:
"Has my WordPress site been hacked, or does it have a vulnerable plugin?"
"Which of my WordPress plugins have known vulnerabilities?"
"Are any backups, config files or keys exposed on my site?"
"Who signed in to my WordPress admin recently?"
What your AI can do with it:
Set up: add a site, walk you through connecting the Relvato WordPress plugin (or a DNS record for other sites), and add the security monitors.
Read: the site's security verdict and briefing, each run's findings, the brief for fixing them, WordPress plugin updates and the activity log.
Act: run the security monitors now, get a safe update for a vulnerable plugin or the one fix a run proposes, applied by an administrator in WordPress, and start quarantine mode after a hack: hourly security runs for 48 hours with plugin updates paused.
Review: ignore a finding you confirm is expected, or report one that's wrong. Every such decision can be undone.
You stay in control. Tools that change your site are marked so your AI asks you first, and your AI never ignores a security finding on its own judgement. It works within your Relvato account's limits and can't skip proving a site is yours. Approving file or script changes, stopping quarantine, choosing who receives alerts, secrets, deleting data and billing stay in the Relvato dashboard.
Sign-in uses your Relvato account, and you can disconnect your AI at any time under MCP connector → Connected assistants.
https://security.relvato.com/api/mcphttps://security.relvato.com/api/mcpsecurity.relvato.comThe AI reads these server instructions before using this connector, every time.
Relvato Security Monitoring watches WordPress sites for hacks, vulnerabilities and exposed files. Through the Relvato WordPress plugin it reads the site from inside: known-vulnerable plugins, themes and core, tampered core, plugin and theme files, unexpected admin accounts and sign-ins, stale backups. From the outside, on any website (WordPress or not), it finds signs of a hack, scripts loaded from unexpected places, mixed content, and sensitive files left public (backups, .env and config files, leaked keys). Monitors run against the real site and run again when it changes. Everything is scoped to the signed-in Relvato account. No site yet ( is empty)? Start there: ask the user for their website's address and whether it runs WordPress, then . Set up: → with goals ["security"] (or + ) → with group "security". Most security monitors need the site's ownership proven: they read the site from inside through the WordPress plugin (vulnerabilities, file integrity, admin accounts and sign-ins), or probe it the way an attacker would (the exposed-files scan, signs of a hack). Until it's proven, can run only the public monitors, by hand, 3 times a day per domain; their results are real runs against the live site, so never call them a test, a trial, a preview or a simulation. Never tell the user a site is monitored, watched or will alert them until ownership is proven ( / say scheduleStarts). Run the public monitors first (nextAction); then tell the user once why proving ownership is worth it (whyProve and unlocks, or notProvenYet on runs) and every way to prove it (proofOptions: the WordPress plugin, Google Search Console, Bing Webmaster Tools, Cloudflare, a meta tag, a DNS record — not just one); then call . Never say ownership is proven before does. Runs go one at a time and take a while: tell the user how long to expect ('s estimatedMinutes and tellUser), read progress.line to them while runs are live, and check back every couple of minutes rather than polling continuously. Read: (verdict), (trend and the Security briefing), (one monitor), / (findings), , (plugin updates and held versions), , , (WordPress sign-ins, accounts, updates, settings), , . Act: / ; (on/off, schedule); (timing and severity only); . This app doesn't change the site: to update or deactivate a vulnerable plugin, or apply the fix a run proposes, give the user the run's link () — an administrator applies it from there, in WordPress, and Relvato re-runs the monitors to confirm. After a hack or a cleanup: (48 hours of hourly security runs, plugin updates paused), . Review: only when the user confirms a finding is expected ( undoes it); when they say a finding is wrong; for a failure Relvato AI set aside that the user says is real. Never ignore a security finding on your own judgement: that's how a hack gets silenced. Dashboard only (link the user there): approving file-integrity or script-origin changes; stopping quarantine; who receives alerts and muting; secrets and tokens; deleting anything; billing.
WordPress security monitoring. Relvato Security Monitoring watches your WordPress sites for the things that turn into a breach. Through the Relvato WordPress plugin it reads the site from inside: plugins, themes and WordPress core with known vulnerabilities (most urgent when a flaw is being exploited right now), core, plugin and theme files that changed when nothing should have, admin accounts and sign-ins you didn't expect, and stale backups.
Open its listing in the app's connector directory and connect. Sign in to your account in the browser window that opens. It uses OAuth, so the AI never sees your password. Step-by-step setup for each app is on this page.
The Relvato Security Monitoring MCP server URL is https://security.relvato.com/api/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. Relvato Security Monitoring is published or run by Relvato, so it is the official MCP server. See other official connectors.
It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 13,692 of 15,719 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 29 tools: 14 read data, 13 change data and 2 can delete or overwrite data. See every tool and its inputs.
Yes. 13 tools can change data and 2 tools can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:
It comes with 3 skills. A skill tells the AI how to do one job well with these tools. Read each SKILL.md.
No. Its answers come back as text in the chat. Connectors with interactive UI.
This page updates every day. To ask about Relvato Security Monitoring from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.