← Index

io.github.Sahib-Sawhney-WH/looking-glass-mcp

io.github.Sahib-Sawhney-WH/looking-glass-mcp·v3.1.1·Browser Automation

AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

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 →

Environment variables
BROWSER_HEADLESS

Run browser in headless mode

BROWSER_SECURITY_PROFILE

Security profile: restricted, local-dev, open, or sandbox

VAULT_ENCRYPTION_KEY
secret

Passphrase for credential vault encryption (32+ chars). Store credentials via CLI: npx looking-glass-mcp vault store <profile>

MCP quality score · maturity, not trust · methodology
freshness
21
completeness
10
installability
25
documentation
15
stability
10
Alternatives in Browser Automation