What is PageVitals MCP?

It's an MCP (Model Context Protocol) server that connects PageVitals to your AI, giving the agent tools to act on your data — through a single remote link.

Which AI clients does it work with?

Any MCP-compatible client: Claude (web, desktop and mobile), Cursor, ChatGPT with connectors, OpenClaw and other agents.

No. Paste the remote URL into your client, authenticate once, and you're done — no packages to install, no code to write.

Is it secure? Can the AI change my data?

Access is authorized by you and can be revoked anytime. Permissions follow what PageVitals exposes; you approve them when connecting.

How much does it cost?

You start free and upgrade when you need more usage. Billing and limits are managed in your mcp.ai account.

Can I cancel anytime?

Yes. Plans are monthly and can be cancelled at any time, with no lock-in.

PageVitals MCP Server and REST API

PageVitals

Connect your PageVitals account and use 28 tools for analytics straight from your AI agent. Connect with your own API key. PageVitals provides website performance monitoring, synthetic testing, real-user monitoring reports, performance budgets, and optimization insights.

Install in your client

MCP server URL

https://api.mcp.ai/p_page_vitals

Secure connection via OAuth 2.0

Tools (28)

For developers

API & agent docs

Machine-readable docs to plug this server into an agent or call it over REST.

Skill (how to use)

Markdown: use via MCP or via the direct REST API.

Open

llms.txt

Agent-readable spec of this server.

Open

For agents

Install prompt — paste into Claude, ChatGPT, Cursor or any MCP agent and it sets itself up.

Open

Postman collection

Import the REST API into Postman.

Download

FAQ

PageVitals

Tools (28)

API & agent docs

Frequently asked questions

Example prompts

Related tags

PageVitals

Tools (28)

page_vitals_add_configured_pagesAdd one or more explicitly supplied pages to PageVitals monitoring for a website. This persistent bulk operation can consume monitored-page quota and cause future synthetic tests, so call it only when

page_vitals_create_budgetCreate a persistent PageVitals performance budget for a website. This changes monitoring and may change owner alerting behavior, so call only when the user explicitly requests the budget and supplies

page_vitals_create_multistep_testCreate an empty PageVitals multistep test definition with an explicit name and device profile. This only saves persistent configuration: it does not run the test, trigger any synthetic checks, or cons

page_vitals_create_websiteAdd a domain to the PageVitals account and begin managing it. This may consume website quota and start monitoring, so call only when the user explicitly asks to add the domain.

page_vitals_delete_budgetDelete one PageVitals performance budget and stop enforcing its threshold. This is a destructive alerting mutation; use only when the user explicitly selects the exact budget ID for deletion.

page_vitals_delete_configured_pagePermanently delete one PageVitals configured page and all of its test results, including historical results. This is irreversible; use only for an explicit request naming the exact website ID and conf

page_vitals_delete_multistep_testPermanently delete one PageVitals multistep test definition. This is irreversible; use only when the user explicitly identifies the exact website ID and test ID.

page_vitals_delete_websitePermanently delete one PageVitals website and all of its tests, metrics, analytics, and configuration. This is irreversible; use only for an explicit request naming the exact website ID.

page_vitals_get_multistep_testGet one multistep test definition, including its configured steps.

page_vitals_get_page_metricsGet the latest Lighthouse and Chrome UX metrics for one configured page and device.

page_vitals_get_page_opportunitiesList Lighthouse improvement opportunities for a page/device, or return the full variable-shape details for one opportunity ID.

page_vitals_get_page_timelineGet one historical timeline for a page/device: combined loading metrics, CrUX, network bytes, CPU time, or Google Search performance. Google Search requires that integration on the website.

page_vitals_get_testGet the detailed Lighthouse, timing, resource, budget, and validation summary for one synthetic test. Provider values, nulls, metric scales, and JSON-looking strings are returned unchanged.

page_vitals_get_test_reportGet one specialized synthetic-test report: keyed Lighthouse opportunities, the request waterfall, or grouped HTML validation findings. Validation always omits the embedded raw HTML.

page_vitals_get_test_seriesGet one synthetic test series and its individual tests, statuses, page IDs, device variants, and failure messages.

page_vitals_list_budgetsList performance budgets, current status, notification settings, and affected pages for a website.

page_vitals_list_configured_pagesList the raw pages configured for PageVitals monitoring on a website.

page_vitals_list_multistep_runsList historical runs for one multistep test, including status, duration, interaction, layout-shift, CPU, transfer-size, and blocking-time metrics.

page_vitals_list_multistep_testsList multistep tests configured for a website with recent metrics, state, and success rates. A website with no configured multistep tests returns an empty tests list.

page_vitals_list_page_metricsList every configured page/device combination for a website with recent timeline and latest performance metrics.

page_vitals_list_test_seriesList recent synthetic test series for a website, including status and failure counts.

page_vitals_list_website_opportunitiesList Lighthouse improvement opportunities aggregated across a website and the affected pages.

page_vitals_list_websitesList websites visible to the connected PageVitals API key. Use the returned website IDs with all website-scoped tools.

page_vitals_run_multistep_testsTrigger exactly one named multistep test or intentionally fan out to every multistep test configured for a website. Every triggered run consumes PageVitals test quota and may incur cost. Choosing targ

page_vitals_run_test_seriesTrigger synthetic tests for selected page/device variants, or for every configured test when pages is omitted. This action consumes PageVitals test quota and may incur cost; call it only when the user

page_vitals_update_budgetReplace a PageVitals performance budget's complete metric threshold and device scope. This may change monitoring alerts or notifications. Read the current budget first, use its exact website and budge

page_vitals_update_configured_pageUpdate a configured PageVitals page's URL, display alias, or both. This changes persistent monitoring configuration; use the exact page ID from List Configured Pages and provide at least one new value

page_vitals_update_multistep_testUpdate a multistep test's alias and device. Both fields are required because PageVitals PUT replacement and partial-update semantics were not safely live-tested; read the current test first when prese

API & agent docs

Frequently asked questions

What is PageVitals MCP?

Which AI clients does it work with?

Do I need to code?

Is it secure? Can the AI change my data?

How much does it cost?

Can I cancel anytime?

Example prompts

Related tags