metaharness_flywheel
ADR-322 — evaluate candidates into immutable receipts, inspect the append-only promotion ledger, and explicitly promote one signed receipt with atomic compare-and-swap semantics. Use when running governed flywheel evaluation or promotion; evaluation never mutates the active champion, and promotio...
This record as markdown: /tools/io-github-ruvnet-claude-flow/metaharness-flywheel.md
What metaharness_flywheel does on Claude Flow
AI agents call metaharness_flywheel to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why metaharness_flywheel is rated Low
Even though metaharness_flywheel only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs metaharness_flywheel safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For metaharness_flywheel, this is the rule to start with:
metaharness_flywheel is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every metaharness_flywheel call is checked against it from then on.
Questions about metaharness_flywheel
ADR-322 — evaluate candidates into immutable receipts, inspect the append-only promotion ledger, and explicitly promote one signed receipt with atomic compare-and-swap semantics. Use when running governed flywheel evaluation or promotion; evaluation never mutates the active champion, and promotion requires confirm=true plus a locally approved Ed25519 public-key PEM path. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for metaharness_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 Claude Flow. Nothing to install.
metaharness_flywheel is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the metaharness_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 metaharness_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.
metaharness_flywheel is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue