High-risk tools in Superglue MCP
4 of the 21 tools in Superglue MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
run_toolExecuteExecutes a tool — either a draft (by draftId) or a saved tool (by toolId), not both. Keep JSON payload data in payload and bind uploaded files separately in files. Set includeSt...
-
authenticate_oauthExecuteInitiates OAuth flow for a system. Credentials (client_id/secret) must already be stored on the system. On success, tokens are auto-saved.
-
call_systemExecuteExplore APIs, databases, and file servers, verify authentication, test endpoints, and examine response formats. Load the relevant protocol skill first. Only call ONE AT A TIME. ...
-
test_role_accessExecuteTest a custom rule expression against a sample stepConfig. Evaluates a JS expression locally (no server call) to verify it returns the expected allow/block result before adding ...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.