io.github.tiliondev/fortress
Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean 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 →
TILION_MCP_PREWARMBoot the browser at startup so the first tool call is instant (default 1).
TILION_MCP_HEADLESSSet 0 to show a visible browser window (default 1).
TILION_ALLOW_PRIVATE_EGRESSSet 1 to allow tools to reach localhost / private IPs (SSRF guard off).
TILION_BASE_URLRun browsers on a hosted Tilion server instead of locally.
TILION_API_KEYBearer key for the hosted Tilion server (cloud mode only).
Web scraping for AI agents: fetch any page via proxy or full browser, past anti-bot defenses.
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…