Publisher · GitHub organization

chromedevtools

github.com/chromedevtools ↗Last audit 26 Oct 2026

chromedevtools publishes 2 MCP servers and 6 agent skills on the atlas: 8 SAFE, 0 CAUTION, 0 BLOCK, with a mean score of 88/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “chromedevtools: skills and MCP servers”. Retrieved 26 Oct 2026. https://modelsatlas.com/orgs/chromedevtools
Listings
8

2 MCP servers · 6 skills

Mean score
88 / 100

mean of the audit scores

Findings
51

across all listings

Stars
430K

on the listed repositories

SAFE 8CAUTION 0BLOCK 0

Everything chromedevtools publishes here

Most stars first · stamps show the audited version

Troubleshootingchromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 26 Oct 2026
Memory Leak Debuggingchromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 24 Oct 2026
Debug Optimize Lcpchromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 23 Oct 2026
Chrome Devtools Clichromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 22 Oct 2026
Chrome Devtoolschromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 21 Oct 2026
A11y Debuggingchromedevtools/chrome-devtools-mcp
Skill ★ 54K
✓SAFEB · 89 · 20 Oct 2026
chrome-devtools-mcpChromeDevTools/chrome-devtools-mcp
MCP ★ 54K
✓SAFEB · 84 · 20 Oct 2026
Chrome DevToolschromedevtools/chrome-devtools-mcp
MCP ★ 52K
✓SAFEB · 84 · 19 Sep 2026

Questions

Are chromedevtools's MCP servers and skills safe to install?
Of 8 listings, 8 are SAFE, 0 CAUTION and 0 BLOCK, with a mean score of 88 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about chromedevtools?
It collects every skill and MCP server on the atlas whose source lives under github.com/chromedevtools, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.