run_mandatory_flywheel
Enforce the mandatory 6-step AI Flywheel verification after any non-trivial change. All 6 steps must pass before work is considered done. Skipping is only allowed for trivial changes (typo, comment, config) with explicit justification. Real-world example: a variety-check dead-code bug was only ca...
This record as markdown: /tools/io-github-homenshum-nodebench/run-mandatory-flywheel.md
What run_mandatory_flywheel does on Nodebench
AI agents invoke run_mandatory_flywheel to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why run_mandatory_flywheel is rated High
This tool executes a complex verification workflow with conditional branching (mandatory vs. skippable based on change type). While it doesn't directly delete or move money, it enforces gates that can block or approve deployments—a consequential operation. Severity is high because misconfiguration or misuse could either block legitimate work or inappropriately skip critical safety checks.
From the tool's definition Tool enforces a mandatory verification process that 'must pass before work is considered done' and explicitly allows skipping with 'justification'.
Attacks that exploit this kind of access
The rule that runs run_mandatory_flywheel safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_mandatory_flywheel, this is the rule to start with:
run_mandatory_flywheel stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every run_mandatory_flywheel call is checked against it from then on.
Questions about run_mandatory_flywheel
Enforce the mandatory 6-step AI Flywheel verification after any non-trivial change. All 6 steps must pass before work is considered done. Skipping is only allowed for trivial changes (typo, comment, config) with explicit justification. Real-world example: a variety-check dead-code bug was only caught by running this process after smoke tests passed. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for run_mandatory_flywheel: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nodebench. Nothing to install.
run_mandatory_flywheel is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_mandatory_flywheel rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_mandatory_flywheel. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_mandatory_flywheel is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue