save_skill · Code Execution MCP: Risk & Policy

WHAT IT DOES

What save_skill does on Code Execution MCP

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

WHY IT NEEDS A POLICY

Why save_skill needs a policy

This tool creates or persists skill definitions (reversible writes) rather than destructively deleting them or executing arbitrary code. In the context of a code execution MCP with skill persistence, saving a skill modifies stored state but does not execute arbitrary operations or irreversibly delete data.

From the tool's definition Tool name 'save_skill' indicates creation or modification of skill objects. Server description mentions 'skills persistence' as a core feature, confirming that skills are stored and managed. Empty description limits certainty but naming is explicit.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_skill Rate-limited

save_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": {
    "save_skill": {
      "limits": [
        {
          "counter": "save_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 Code Execution MCP, so you can run agents against it safely.

FAQ

Questions about save_skill

What does the save_skill tool do? +

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

How do I enforce a policy on save_skill? +

Register the Code Execution MCP server in PolicyLayer and add a rule for save_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 Code Execution MCP. Nothing to install.

What risk level is save_skill? +

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

Can I rate-limit save_skill? +

Yes. Add a rate_limit block to the save_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 save_skill completely? +

Set action: deny in the PolicyLayer policy for save_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 save_skill? +

save_skill is provided by the Code Execution MCP server (marc-shade/code-execution-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.