What it does
Zendriver MCP exposes browser automation to LLM agents over the Model Context Protocol. The publisher describes it as undetectable browser automation, so an agent can drive a web browser through MCP tool calls rather than through direct scripting.
It fits workflows where an AI agent needs to open pages, interact with them and read results as part of a larger development or research task. The publisher's description is brief, so the specific tools and supported actions are not stated here; the project page on GitHub is the place to check them.
Running it means connecting the server to an MCP-compatible client and installing its dependencies as described in the repository. The publisher's material does not list further setup steps.
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
Zendriver MCP
Undetectable browser automation for LLM agents, spoken over MCP.
v0.3.4As shown on registry.modelcontextprotocol.io when we last read it