install_hooks · Zikkaron MCP: Risk & Policy

WHAT IT DOES

What install_hooks does on Zikkaron

AI agents use install_hooks to create or update resources in Zikkaron — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zikkaron environment.

WHY IT NEEDS A POLICY

Why install_hooks needs a policy

An AI agent can call install_hooks faster than any human can review — one bad instruction and it creates or modifies resources in Zikkaron by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

install_hooks Rate-limited

install_hooks stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "install_hooks": {
      "limits": [
        {
          "counter": "install_hooks_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about install_hooks

What does the install_hooks tool do? +

install_hooks. It is categorised as a Write tool in the Zikkaron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on install_hooks? +

Register the Zikkaron MCP server in PolicyLayer and add a rule for install_hooks: 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 Zikkaron. Nothing to install.

What risk level is install_hooks? +

install_hooks is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit install_hooks? +

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

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

install_hooks is provided by the Zikkaron MCP server (pypi:zikkaron). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.