add_skill · Zanat MCP: Risk & Policy

WHAT IT DOES

What add_skill does on Zanat

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

WHY IT NEEDS A POLICY

Why add_skill needs a policy

This tool performs a reversible creation/modification operation on the skill hub (adding skills). While it doesn't delete or overwrite existing data, it creates new state. The most relevant category is Write because the action creates or adds entries to the system and can be undone (via remove_skill).

From the tool's definition The tool 'add_skill' explicitly creates or adds a skill to the hub. The description states it can 'Add a skill' with optional pinning to tags or commits, indicating it modifies the skill configuration in the hub.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_skill Rate-limited

add_skill 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": {
    "add_skill": {
      "limits": [
        {
          "counter": "add_skill_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 Zanat, so you can run agents against it safely.

FAQ

Questions about add_skill

What does the add_skill tool do? +

Add a skill from the hub. Omit skill_name to add all skills not yet added. Optionally pin to a specific tag or commit SHA. It is categorised as a Write tool in the Zanat MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_skill? +

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

What risk level is add_skill? +

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

Can I rate-limit add_skill? +

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

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

add_skill is provided by the Zanat MCP server (@iamramo/zanat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.