Public Browser – a Chrome MCP server with ~40% fewer tool calls is a skill AI agent for Reduce the number of tool calls during AI browser agent execution to cut costs and improve performance. Pricing: Not specified. As of 2026-11-06, KanonAgent records 2 upvotes. First indexed by KanonAgent on 2026-09-15.
A lightweight Chrome MCP server that reduces tool calls by ~40%, improving AI workflow efficiency.
2 upvotes
Tracked by Kanon since Sep 15, 2026
Status basis: npm_downloads_7d momentum fell to 1 per 3d from 64 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to 1 per 3d from 64 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 4 per 3d from 96 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 52 in the last 3d vs 23 in the 3d before (ratio 2.3x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 4 per 3d from 96 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 64 in the last 3d vs 11 in the 3d before (ratio 5.8x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 64 in the last 3d vs 11 in the 3d before (ratio 5.8x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -61 per 3d from 44 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -61 per 3d from 42 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 52 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 44 in the last 3d vs 20 in the 3d before (ratio 2.2x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 52 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 42 in the last 3d vs 22 in the 3d before (ratio 1.9x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -223 per 3d from 35 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -214 per 3d from 25 (<= 40% of the prior window)
- Anomaly daily change -145.0 is -4.1 standard deviations from this entity's own prior mean (13.2±38.5, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -135 per 3d from 14 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 35 per 3d from 93 (<= 40% of the prior window)
- Anomaly daily change -145.0 is -4.1 standard deviations from this entity's own prior mean (13.2±38.5, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 25 per 3d from 259 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -6 per 3d from 270 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -6 per 3d from 270 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 259 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 270 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change -123.0 is -7.2 standard deviations from this entity's own prior mean (11.4±18.6, baseline excludes this point) — unusual, not necessarily adoption
🔎 Known / Unknown
11 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | chrome,mcp | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneReduce the number of tool calls during AI browser agent execution to cut costs and improve performance.
AutonomyL2 · tool-calling(evidence: "browser-automation…")
Who it is forDevelopers and AI automation engineers
Prerequisitesopen source · self-hostable
Integrationschrome · mcp
PricingNot specified
Traction · why it is risingOptimizes AI agent communication efficiency with measurable reduction in tool usage
Why it matters
It’s a critical performance layer in agent ecosystems, improving reliability and cost-efficiency at the infrastructure level.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“One command to install, zero config.”— readme
“browser-automation”— topics
“A lightweight Chrome MCP server”— description
“Built for Claude Code, Cursor, and any MCP-compatible client.”— readme
“Lets Claude Code and Cursor drive Chrome”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Building Public Browser? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is Public Browser?
A lightweight Chrome MCP server that reduces tool calls by ~40%, improving AI workflow efficiency.
What does Public Browser do?
Reduce the number of tool calls during AI browser agent execution to cut costs and improve performance.
Why does Public Browser matter?
It’s a critical performance layer in agent ecosystems, improving reliability and cost-efficiency at the infrastructure level.
How much does Public Browser cost?
Not specified
Is Public Browser open source?
Yes — Public Browser is open source.
Can I self-host Public Browser?
Yes — Public Browser can be self-hosted.
What does Public Browser integrate with?
chrome,mcp
How popular is Public Browser?
As tracked by KanonAgent: 2 upvotes (first indexed 2026-09-15).
What are the best Public Browser alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, archify, open-design, deer-flow, ruflo, career-ops.