What it does
The publisher describes agentic-browser as a way to give any AI agent access to the user's real Chrome browser. It perceives pages through their text rather than only through visual input, and it shows a visible cursor so the agent's actions on the page can be followed. The publisher reports about four times fewer tokens.
It suits agents that need to work inside a browser the user already has open, rather than in a separate, clean browser session. The source does not describe setup steps or further configuration.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.davarion-tech/agentic-browser
Give any AI agent your real Chrome: text perception, visible cursor, ~4x fewer tokens.
v1.4.0As shown on registry.modelcontextprotocol.io when we last read it