Security review

Is ai.smithery/browserbasehq-mcp-browserbase MCP safe to give an agent?

read onlyverifiedverifiedhealthy

A factual risk summary built from ai.smithery/browserbasehq-mcp-browserbase’s real tool surface, execution model, and verification history — not a vibe. Trust score 80/100.

01What it can do

Only read-style tools observed — no write/destructive tools.

6 tools observed

02Execution model

Runs on the vendor's infrastructure; you connect over the network. No untrusted code runs on your machine, but you grant the hosted service access.

Installs via npx (`npx -y @browserbasehq/mcp`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Scrape a website · write

The write/destructive access this server can exercise, inferred from its verified tools.

04Verification

handshakepassed — tool surface is real

runstools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed

last_checked2026-08-16 18:46Z

sourcesOfficial MCP Registry [p1] · Awesome MCP Servers (wong2) [p6]

Reduce the risk

Worried about handing an agent raw access? See governed agents in action — Apex gives your AI paced, capped, fully-logged hands with approval queues before anything runs.

Explore Apex →

See also: full server page · setup · alternatives