High-risk tools in Mcp
4 of the 12 tools in Mcp 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
-
agent_buildExecuteHand a natural-language prompt to the FreeAppStore VibeCode AGENT — the platform's own AI writes the code AND deploys it. This is different from create_app/update_files (where t...
-
app_logsExecuteQuery recent logs for an app — errors, warnings, SDK calls, build info. Requires authentication (app owner).
-
deploy_statusExecuteCheck the deploy status of an app (last 5 GitHub Actions runs). No auth needed for public repos.
-
platform_guideExecuteGet the FreeAppStore platform guide (SKILLS.md) for AI-assisted development. Returns the full guide that tells you how to build apps on the platform.
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.