skills_refresh_index · Skills MCP: Risk & Policy

WHAT IT DOES

What skills_refresh_index does on Skills

AI agents invoke skills_refresh_index to trigger actions in Skills. 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 skills_refresh_index needs a policy

This tool triggers a rebuild operation of an in-memory index by re-reading files from disk. It executes an indexing process whose effects depend on the current state of files on disk. It is not a simple read (it actively rebuilds state), not a write to persistent data, and not destructive (the index can be rebuilt again).

From the tool's definition Rebuild the in-memory skill index and search corpus. Use this after adding, removing, or modifying skill files on disk.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

skills_refresh_index Rate-limited

skills_refresh_index 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": {
    "skills_refresh_index": {
      "limits": [
        {
          "counter": "skills_refresh_index_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 Skills, so you can run agents against it safely.

FAQ

Questions about skills_refresh_index

What does the skills_refresh_index tool do? +

Rebuild the in-memory skill index and search corpus. Use this after adding, removing, or modifying skill files on disk. Returns the number of skills indexed and how long the rebuild took. It is categorised as a Execute tool in the Skills MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on skills_refresh_index? +

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

What risk level is skills_refresh_index? +

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

Can I rate-limit skills_refresh_index? +

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

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

skills_refresh_index is provided by the Skills MCP server (lucasromanzin/skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.