The Google PageSpeed MCP for performance monitoring on autopilot
Connect one Google API key and full Lighthouse audits (performance, accessibility, best practices, SEO) become a workflow step you can schedule, branch on, and report from.
What the Google PageSpeed Insights MCP connector does
The Google PageSpeed Insights connector for Mattering Automations wraps the PageSpeed Insights API in a single focused node: give it a URL and a strategy (mobile or desktop) and it returns the full Lighthouse result, category scores included.
The node speaks MCP, the open protocol for connecting AI assistants to tools, so Claude, ChatGPT, and any MCP-capable assistant can run audits through it, alongside Matter, the AI assistant built into the platform. Ask an assistant why a page is slow and it can pull the actual Lighthouse data before answering.
One node sounds small until it is on a schedule: page speed regressions are the kind of thing nobody notices until rankings slip, and a weekly audit that opens a task when the score drops turns that into routine maintenance.
One connection, three surfaces
- Visual automations. Drag Google PageSpeed Insights nodes onto the canvas and wire them to triggers, conditions, and other apps.
- AI agents, yours or ours. These nodes speak MCP, the open protocol, so Claude, ChatGPT, and any MCP-capable assistant can use them, and Matter, the agent built into the platform, uses them natively.
- The whole platform. Combine with native tasks, projects, and other connectors, no middleware in between.
Every Google PageSpeed Insights node, ready to drop on the canvas
1 nodes, generated from the connector itself so this list always matches what ships. Expand a category to browse.
Read and query nodes 1
PageSpeed Analyze
Run a Lighthouse PageSpeed Insights analysis for a URL (performance, accessibility, best practices, SEO, PWA).
Connecting Google PageSpeed Insights takes one credential
Create an API key in the Google Cloud console under APIs and Services, then Credentials, with the PageSpeed Insights API enabled on the project. The PageSpeed Insights API is free to use.
In the Google Cloud console, enable the PageSpeed Insights API on your project.
Create an API key under APIs and Services, then Credentials.
In Mattering Automations, open Connectors, choose Google PageSpeed Insights, and create a credential with the key.
The PageSpeed Analyze node appears in the canvas palette, ready to use.
Common uses for the Google PageSpeed Insights MCP
Weekly performance audits
Run Lighthouse against your key pages on a schedule and write the category scores into a Mattering database for a trend line you actually keep.
Regression alerts
Branch the workflow when the performance score drops below your threshold and open a task with the failing audit attached, so a regression becomes assigned work the day it happens.
Post-deploy checks
Audit the pages a release touched and post the before and after scores where the team will see them.
Competitor benchmarking
Audit competitor pages alongside your own on the same schedule; the API works on any public URL.
Agent-driven diagnostics
An MCP-connected assistant can pull the audit for a slow page and read the specific failing audits before recommending fixes, instead of guessing.
Example: Performance regressions become tasks automatically
Built on the Automations canvas in a few minutes, or described in plain language to Matter and built for you.
Trigger: a weekly schedule fires.
Google PageSpeed: Analyze runs a mobile audit for each monitored URL.
A condition checks whether any performance score fell below the threshold.
Mattering Productivity: a task is created per regression with the scores and the audit details, assigned to the site owner.
Google PageSpeed Insights MCP questions, answered
Can an AI agent run Lighthouse audits through this MCP?
Yes. Matter and any MCP-connected assistant, including Claude and ChatGPT, can run the PageSpeed Analyze node and read the full Lighthouse result, the same node available on the automation canvas.
Does this work with Claude, ChatGPT, or other AI assistants?
Yes. Mattering exposes this node over MCP, an open protocol for connecting AI assistants to tools, so any MCP-capable assistant can connect to your workspace and use it. Matter, the assistant built into the platform, uses it natively.
What does the node return?
The PageSpeed Insights API response including the Lighthouse result: category scores for performance, accessibility, best practices, SEO, and PWA, plus the underlying audits. You choose mobile or desktop strategy and which categories to run per call.
Does it cost anything?
The PageSpeed Insights API is free from Google. Google applies request quotas to keys, and Google's documentation is the source of truth for current limits; scheduled auditing of a normal page set sits comfortably inside them.
What credential does it use?
A Google Cloud API key with the PageSpeed Insights API enabled, sent as a query parameter and stored encrypted in Google Secret Manager. One key can serve the other Google API-key connectors on the platform too.
Can it audit pages behind a login?
No. PageSpeed Insights fetches the URL from Google's infrastructure, so only publicly reachable pages can be audited.
Put Google PageSpeed Insights to work inside your workspace
Connect once, then use every node in visual automations and AI agent workflows across the Mattering platform.
All product names, logos, and brands are property of their respective owners and are used for identification purposes only. Use of these names, logos, and brands does not imply endorsement or affiliation. Google PageSpeed Insights is a product of its respective owner; Mattering is an independent platform.