docs_refresh · Docs MCP: Risk & Policy

WHAT IT DOES

What docs_refresh does on Docs

AI agents invoke docs_refresh to trigger actions in Docs. 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 docs_refresh needs a policy

This tool triggers an active filesystem scan operation rather than simply reading pre-indexed data. It performs an external operation (rescanning the filesystem) whose effects depend on what packages are currently installed. No data is deleted or modified, no financial action occurs, and no arbitrary code is executed, but it does execute a discovery/indexing process.

From the tool's definition Re-scan the filesystem for docs. Call this after installing or updating a @particle-academy/* package mid-session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docs_refresh Rate-limited

docs_refresh 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": {
    "docs_refresh": {
      "limits": [
        {
          "counter": "docs_refresh_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 Docs, so you can run agents against it safely.

FAQ

Questions about docs_refresh

What does the docs_refresh tool do? +

Re-scan the filesystem for docs. Call this after installing or updating a @particle-academy/* package mid-session. It is categorised as a Execute tool in the Docs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on docs_refresh? +

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

What risk level is docs_refresh? +

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

Can I rate-limit docs_refresh? +

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

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

docs_refresh is provided by the Docs MCP server (particle-academy/docs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.