Product Lead for @ChromeDevTools. Ideas my own. he/him
Joined November 2013
- Tweets 1,735
- Following 275
- Followers 1,146
- Likes 1,109
125 Photos and videos
Michael Hablich retweeted
May 13
That’s a first: GitHub’s Advisory Database (incorrectly) flags Puppeteer as malware. github.com/github/advisory-d… We are no longer able to publish new releases.
Anyone at @github or @Microsoft who can escalate this, please?
3
10
50
11,999
Apr 21
We are entering the era of dual interface products:
- Rich UI for humans
- Token efficient API for agents
Your API is costing agents money.
I'm speaking at Agentic DevDays in Stockholm on April 28 to share how we are addressing this for @ChromeDevTools .
50
Michael Hablich retweeted
Apr 12
Want to give your agent quality checks?
Chrome's DevTools MCP now includes:
⚡️ Performance checks via Lighthouse
📈 Memory leak detection Skill
🦻 Accessibility debugging Skill
🎨 LCP optimization Skill
and an experimental new CLI 👀
41
151
1,227
129,746
Feb 25
@mistralvibe I would love to get working setup instructions for Mistral Vibe added to github.com/ChromeDevTools/ch… ... want to open a PR and cc me please?
3
1
3
2,785
Mar 29
Oh, that's going to be interesting (in a good way)
Mar 28
The next version of OpenClaw is also an MCP, you can use it instead of Anthropic's message channel MCP to connect to a much wider range of message providers.
(I know, this is awkward)
102
Mar 23
Your #AI agent isn't picking the wrong tool because it's dumb. It's picking the wrong tool because your description didn't help it pick the right one.
Link: hablich.dev/articles/discove…
54
Mar 19
Wrote about something that's been on my mind: every browser #AI agent tool runs on CDP, which has zero auth. The security story is entirely in the layers around it. Checkout hablich.dev/articles/trust-b…
32
Mar 18
1. We spent a decade building web performance metrics around human perception.
Turns out they matter just as much when your user is an AI agent.
The reasons are completely different. 🧵
2
1
127
Mar 18
6. The mental models still hold: set a budget, measure, optimize the critical path.
But the budgets change, the measurements change, and what counts as "critical" changes when the user doesn't have eyes.
1
27
Michael Hablich retweeted
Every web developer's agent workflow: copy console error, paste into agent, wait, repeat.
Chrome DevTools MCP fixes this: ~25 tools that give your coding agent direct access to the browser.
@nearestnabors talked to @MHablich about how they built it.
youtu.be/CIOcjjgl9MI
3
5
8
1,560
Jan 28
CLI wrappers for common MCP tools is great. It only provides an optimization for half of the challenge though. What about optimizing data orchestration?
The team is thinking about extending the Chrome DevTools MCP server with GraphQL support. Let us know what you think on the RFC: github.com/ChromeDevTools/ch… 🔎🗂️
1
130
Michael Hablich retweeted
The team is thinking about extending the Chrome DevTools MCP server with GraphQL support. Let us know what you think on the RFC: github.com/ChromeDevTools/ch… 🔎🗂️
2
9
30
5,101
Jan 19
#MCP is great for agent-to-tool communication. But 50 sequential browser operations = 50 round trips = latency and token overhead.
I opened an RFC for a CLI wrapper that lets agents batch operations via bash scripts.
github.com/ChromeDevTools/ch…
#AIagents
3
8
2,514
Michael Hablich retweeted
12 Dec 2025
Let your coding agent debug your active browser session directly → goo.gle/4iSz0PV
This new Chrome DevTools MCP enhancement lets you seamlessly switch between manual and AI-assisted debugging for faster fixes.
16
69
530
37,078
11 Dec 2025
People might appreciate this, at least plenty of people requested this feature: developer.chrome.com/blog/ch…
1
4
3,388