High-risk tools in Claude Code MCP - Agent Orchestration Platform
3 of the 9 tools in Claude Code MCP - Agent Orchestration Platform 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
-
create_agentExecuteCreate new Claude Code agent with comprehensive iTerm2 and process management
-
send_message_to_agentExecuteSend message to agent with automatic ADDER+ prompt injection and coordination
-
start_new_agent_conversationExecuteStart new agent conversation with context restoration coordination
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.