me.openbrowser/openbrowser-ai
AI browser automation. Write async Python to navigate, click, type, and extract data.
Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
OPENBROWSER_HEADLESSRun browser in headless mode (true/false)
OPENBROWSER_ALLOWED_DOMAINSComma-separated list of allowed domains (empty for no restrictions)
OPENBROWSER_USER_DATA_DIRChrome profile directory for persistent browser sessions
OPENBROWSER_STORAGE_STATEJSON file used to save and restore cookies plus localStorage between MCP restarts
OPENBROWSER_COMPACT_DESCRIPTIONUse minimal tool description (~500 tokens instead of ~1,430)
OPENBROWSER_MAX_OUTPUTMaximum output characters per code execution (default: 10000)
ANONYMIZED_TELEMETRYEnable anonymized usage telemetry (true/false)
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…
Sign, fill, merge and split PDFs entirely in your browser - files never leave your device.