High-risk tools in Myco — Agent-First Cognitive Substrate

High severity Myco — Agent-First Cognitive Substrate MCP Server 2 of 21 tools

2 of the 21 tools in Myco — Agent-First Cognitive Substrate 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

myco_advance_cycle Execute

Run one substrate metabolic cycle. Triggers gradient advance, fruiting checks, and sporocarp emission. Returns the list of fruited axes and the sporocarps emitted (each with typ...
myco_run_immune_check Execute

Trigger an ad-hoc immune verification scan. The substrate runs comprehensive integrity checks (substrate_id well-formedness, DAG hash-chain integrity, cycle-counter monotonicity...

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.

Destructive Action Autonomy
Runaway Tool Loops
Prompt Injection via Tool Results

High-risk tools in Myco — Agent-First Cognitive Substrate

Tools at high risk

Attacks that target this class

More on Myco — Agent-First Cognitive Substrate

Enforce policy on every Myco — Agent-First Cognitive Substrate tool call.