AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
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.
TESTORIM_API_KEYAPI keyrequiredTestorim API key (Settings, API keys in the app). Starts with tst_live_.
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
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.
list_projectsList the projects (sites under test) in the API key's workspace, with each project's id and address.List the projects (sites under test) in the API key's workspace, with each project's id and address.
No input schema was published for this tool.
list_testsList the saved tests (procedures) of a project. A saved test replays its recorded steps without re-planning, so it is faster and repeatable.List the saved tests (procedures) of a project. A saved test replays its recorded steps without re-planning, so it is faster and repeatable.
No input schema was published for this tool.
run_testRun a test in a real browser and return the verdict, the failing steps with the reason for each, the written report and links to the evidence. Pass testId to replay a saved test, or description to test anything in plain English, for example: "Sign up with a new email address and check that the dash…Run a test in a real browser and return the verdict, the failing steps with the reason for each, the written report and links to the evidence. Pass testId to replay a saved test, or description to test anything in plain English, for example: "Sign up with a new email address and check that the dash…
No input schema was published for this tool.
get_runRead a run's status, verdict, failing steps, report and evidence links.Read a run's status, verdict, failing steps, report and evidence links.
No input schema was published for this tool.
cancel_runStop a queued or running run. A cancelled run has no verdict.Stop a queued or running run. A cancelled run has no verdict.
No input schema was published for this tool.
create_projectCreate a project for a site so it can be tested. If the workspace already tests that address, the existing project is returned instead.Create a project for a site so it can be tested. If the workspace already tests that address, the existing project is returned instead.
No input schema was published for this tool.
testorimNo description publishedThis tool published no description. Forge does not invent one.
6 of 7 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.
AI browser tests from your coding agent: a verdict, failing steps, report, video and trace.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.