13 tools from the Browser Automation MCP Server, categorised by risk level.
View the Browser Automation policy →agent_browser_help Show help for agent-browser, a low-level browser automation CLI for precise, deterministic control. Call this to see available commands. stagehand_extract Extract structured data or text from the current page using an instruction. stagehand_get_url Return the current page URL (full URL with query/fragment). stagehand_observe Find interactive elements on the page from an instruction; optionally return an action. stagehand_screenshot Capture a full-page screenshot and return it (and save as a resource). agent_browser_run Run a low-level browser command. Use over Stagehand when you need precise, deterministic control — element-by-ref interactions, DOM inspection, net... 3/5 stagehand_act Perform a single action on the page (e.g., click, type). 2/5 stagehand_agent Execute a task autonomously using Stagehand agent in hybrid mode. The agent uses both DOM-based and coordinate-based actions for maximum reliability. 3/5 stagehand_navigate Navigate to a URL in the browser. Only use this tool with URLs you're confident will work and be up to date.
Otherwise, use https://google.com ... 3/5 stagehand_run_script Run a Stagehand script file (default export from defineScript) against
the current browser session. Returns {status: "passed"|"failed", durat... 4/5 stagehand_scenario Execute a multi-step test scenario (arrange/act/assert) using the Stagehand agent. Returns structured pass/fail/blocked results per assert step. 3/5 The Browser Automation MCP server exposes 13 tools across 3 categories: Read, Write, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Browser Automation server.
Browser Automation tools are categorised as Read (5), Write (2), Execute (6). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept