metaharness_score

ADR-150 — 5-dimension harness readiness scorecard from

SERVERClaude Flow SOURCEclaude-flow

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

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

WHAT IT DOES

What metaharness_score does on Claude Flow

AI agents call metaharness_score 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.

RISK

Why metaharness_score is rated Low

The tool appears to retrieve or compute a scoring assessment (a form of data retrieval/query) without side effects. The incomplete description ('from' cuts off) limits confidence slightly, but the 'scorecard' terminology strongly suggests a reporting/read operation rather than write, execute, destructive, or financial actions.

From the tool's definition Tool name 'metaharness_score' and description indicate it generates a 'readiness scorecard' — a read-only assessment or evaluation metric. No modification, deletion, execution, or financial operations are implied.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs metaharness_score 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_score, this is the rule to start with:

metaharness_score Allowed

metaharness_score is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "metaharness_score": {}
  }
}

ALLOW ONLY 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_score call is checked against it from then on.

FAQ

Questions about metaharness_score

What does the metaharness_score tool do? +

ADR-150 — 5-dimension harness readiness scorecard from. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on metaharness_score? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for metaharness_score: 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_score? +

metaharness_score is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit metaharness_score? +

Yes. Add a rate_limit block to the metaharness_score 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_score completely? +

Set action: deny in the PolicyLayer policy for metaharness_score. 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_score? +

metaharness_score 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 →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →