policy_approve

Issue a scoped, expiring, limited-use human approval. Use when policy_evaluate returns approval_required; self-approval is rejected.

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/policy-approve.md

WHAT IT DOES

What policy_approve does on Claude Flow

AI agents invoke policy_approve 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 policy_approve is rated High

This tool issues formal approvals that unblock or authorize other actions. It is not merely reading data; it executes an approval decision with real downstream consequences (permitting actions that were previously blocked). Since approvals can authorize destructive, financial, or other high-impact operations, the blast radius is high.

From the tool's definition "Issue a scoped, expiring, limited-use human approval" and "self-approval is rejected" — the tool triggers an authorization/approval action that gates downstream operations

Attacks that exploit this kind of access

RECOMMENDED RULE

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

policy_approve Rate-limited

policy_approve 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": {
    "policy_approve": {
      "limits": [
        {
          "counter": "policy_approve_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 policy_approve call is checked against it from then on.

FAQ

Questions about policy_approve

What does the policy_approve tool do? +

Issue a scoped, expiring, limited-use human approval. Use when policy_evaluate returns approval_required; self-approval is rejected. 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 policy_approve? +

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

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

Can I rate-limit policy_approve? +

Yes. Add a rate_limit block to the policy_approve 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 policy_approve completely? +

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

policy_approve 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

team_manager_approve_plan on Team Manager MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

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