High-risk tools in Mcp Remote Agent
4 of the 16 tools in Mcp Remote Agent 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
-
remote_bashExecuteExecute bash command on remote Linux host. Commands with special chars ($
-
remote_batchExecuteBatch execute multiple operations (read/stat/glob/bash). Max 20 per request, more efficient than multiple individual calls.
-
remote_exec_asyncExecuteAsync execute long-running bash command. Returns taskId immediately, use remote_task to query results.
-
remote_scriptExecuteExecute multi-line script on remote host. Script is written to temp file then executed, completely avoiding bash escaping and encoding issues. Ideal for complex scripts with var...
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.