What it does
Browse Bridge connects AI agents to Chrome browser tabs. According to the publisher, it lets an agent observe and control only the tabs the user has explicitly shared through Browse Bridge, so access to other tabs is not part of the description.
It would be reached for when an agent needs to work with a live browser session, such as reading the state of an open page or acting within a tab the user has chosen to share, rather than working from static content alone.
The publisher's description does not list setup steps, but the resource is an MCP server, so it is run as a server that an MCP-compatible AI agent connects to. Further setup details are available in the project repository.
Limitations and requirements
Only tabs the user explicitly shares through Browse Bridge are accessible to the agent. The publisher's description states no further requirements.
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
Browse Bridge
Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it