metaharness_evolve

SERVERClaude Flow SOURCEclaude-flow

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ruvnet-claude-flow/metaharness-evolve.md

WHAT IT DOES

What metaharness_evolve does on Claude Flow

AI agents invoke metaharness_evolve to trigger actions in Claude Flow. 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.

RISK

Why metaharness_evolve is rated High

This tool executes automated mutations to AI orchestration policies and evaluates outcomes in a sandbox environment, then promotes changes based on measured results. This is an Execute pattern: it triggers external operations (policy mutations, variant scoring, promotion decisions) whose effects depend on runtime arguments and discovered fitness improvements.

From the tool's definition Tool mutates harness policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy) and performs sandbox-scoring and promotion of variants.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs metaharness_evolve 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_evolve, this is the rule to start with:

metaharness_evolve Rate-limited

metaharness_evolve 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "metaharness_evolve": {
      "limits": [
        {
          "counter": "metaharness_evolve_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every metaharness_evolve call is checked against it from then on.

FAQ

Questions about metaharness_evolve

What does the metaharness_evolve tool do? +

ADR-153 — Darwin Mode: mutate one of seven harness policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, promote only measured wins. The WRITE layer that closes the loop ADR-150 opens (score+genome describe; evolve changes). Use when readiness scores are flat and you want to discover WHICH surface mutation moves them, without retraining the foundation model. Bypassing this tool and hand-tuning is wrong because (a) single-degree-of-freedom mutations keep causal attribution clean, (b) the upstream safety layer catches secret/shell-out/network/dynamic-eval patterns before any variant runs (exit 99 = safety-disqualified, propagated verbatim). REQUIRES --confirm; defaults to dry-run plan output. Long-running: timeout scales with generations×children×sandbox-cost. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on metaharness_evolve? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for metaharness_evolve: 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.

What risk level is metaharness_evolve? +

metaharness_evolve is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit metaharness_evolve? +

Yes. Add a rate_limit block to the metaharness_evolve 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.

How do I block metaharness_evolve completely? +

Set action: deny in the PolicyLayer policy for metaharness_evolve. 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.

What MCP server provides metaharness_evolve? +

metaharness_evolve 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.

KEEP EXPLORING

More on Claude Flow, and thousands of servers like it.

This server

All 496 Claude Flow tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →