High-risk tools in Cursor Agent MCP Server
3 of the 7 tools in Cursor Agent MCP Server 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
-
cursor_agent_runExecuteRun cursor-agent with a prompt and desired output format (legacy single-shot).
-
cursor_agent_chatExecuteChat with cursor-agent using a prompt and optional model/force/output_format.
-
cursor_agent_rawExecuteAdvanced: provide raw argv array to pass after common flags (e.g., [
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.