Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
A Model Context Protocol server that gives an LLM a real Chromium browser, records every action it takes toward a stated goal, and hands back a structured trace so the LLM (or a second LLM) can decide whether the goal was actually achieved. Built on Playwright. Five tools, one binary, no cloud dependency. Most browser-tool MCP servers are stateless — the LLM clicks, gets HTML back, repeats.…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
session_startNo description publishedThis tool published no description. Forge does not invent one.
session_actNo description publishedThis tool published no description. Forge does not invent one.
session_observeNo description publishedThis tool published no description. Forge does not invent one.
session_endNo description publishedThis tool published no description. Forge does not invent one.
qa_get_traceNo description publishedThis tool published no description. Forge does not invent one.
0 of 5 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
A Model Context Protocol server that gives an LLM a real Chromium browser, records every action it takes toward a stated goal, and hands back a structured trace so the LLM (or a second LLM) can decide whether the goal was actually achieved. Built on Playwright. Five tools, one binary, no cloud dependency. Most browser-tool MCP servers are stateless — the LLM clicks, gets HTML back, repeats. There's no record of what happened, no way to grade the run after the fact, and no goal context. Every…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.