Browser Automation
Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"mcp-server-browser-automation": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-browser-automation"
],
"env": {
"AGENT_BROWSER_SESSION_NAME": "mcp",
"AGENT_BROWSER_SHOW_WINDOW": "true",
"BROWSER_AUTOMATION_ALLOW_EVAL": "<browser_automation_allow_eval>"
}
}
}
}{
"mcpServers": {
"mcp-server-browser-automation": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-browser-automation"
],
"env": {
"AGENT_BROWSER_SESSION_NAME": "mcp",
"AGENT_BROWSER_SHOW_WINDOW": "true",
"BROWSER_AUTOMATION_ALLOW_EVAL": "<browser_automation_allow_eval>"
}
}
}
}npx -y @mindstone/mcp-server-browser-automationAGENT_BROWSER_SESSION_NAMESession name for browser persistence
AGENT_BROWSER_SHOW_WINDOWSet to 'false' to run the browser headless. Default is visible (true).
BROWSER_AUTOMATION_ALLOW_EVALSet to 1 to register the browser_evaluate tool (off by default for security)
Automate cloud browsers to navigate websites, interact with elements, and extract structured data.…
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
A paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,