High-risk tools in Alexandria

High severity Alexandria MCP Server 6 of 20 tools

6 of the 20 tools in Alexandria 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

alexandria_council Execute 3/5

Run the LLM Council — 5 advisor archetypes (contrarian, first-principles, expansionist, outsider, executor) analyze your task in parallel, then a reviewer identifies blind spots...
alexandria_debate Execute 3/5

Run inter-agent debates for adversarial analysis. Pits agents against each other to stress-test ideas. Modes: adversarial (1v1), panel (1 vs N reviewers), consensus (thesis + an...
alexandria_doctor Execute 3/5

Run a self-diagnostic check on the Alexandria platform. Verifies: API connectivity, provider key status, .alexandria/ project detection, agent catalog loaded, routing responsive...
alexandria_operator Execute 3/5

Run multi-agent goal decomposition. Breaks a high-level goal into 2-6 agent steps and executes them sequentially. Use for complex goals that need multiple specialists working in...
alexandria_premortem Execute 3/5

Run a pre-mortem failure analysis on a plan or task before execution. Returns failure modes with probability, impact, and mitigations. Use before committing to high-stakes plans.
alexandria_run_agent Execute 4/5

Run a specific named Alexandria agent directly on a task. Use this when you know exactly which specialist you want (e.g., "brand-copywriter", "senior-developer"). Supports two m...

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.

High-risk tools in Alexandria

Tools at high risk

Attacks that target this class

More on Alexandria

Enforce policy on Alexandria