permissions__approve · Iris MCP: Risk & Policy

WHAT IT DOES

What permissions__approve does on Iris MCP

AI agents invoke permissions__approve to trigger actions in Iris MCP. 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 IT NEEDS A POLICY

Why permissions__approve needs a policy

This tool approves permissions for Claude Code agents, which can authorize subsequent actions across codebases. Granting permissions to AI agents can enable arbitrary code execution, file system access, or other high-impact operations depending on what is being approved.

From the tool's definition "Permission approval handler for Claude Code" — approves permissions for Claude Code instances

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

permissions__approve Rate-limited

permissions__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": {
    "permissions__approve": {
      "limits": [
        {
          "counter": "permissions__approve_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Iris MCP, so you can run agents against it safely.

FAQ

Questions about permissions__approve

What does the permissions__approve tool do? +

Permission approval handler for Claude Code. It is categorised as a Execute tool in the Iris MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on permissions__approve? +

Register the Iris MCP server in PolicyLayer and add a rule for permissions__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 Iris MCP. Nothing to install.

What risk level is permissions__approve? +

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

Can I rate-limit permissions__approve? +

Yes. Add a rate_limit block to the permissions__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 permissions__approve completely? +

Set action: deny in the PolicyLayer policy for permissions__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 permissions__approve? +

permissions__approve is provided by the Iris MCP server (jenova-marie/iris-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.