clone_instrument · Redcap MCP: Risk & Policy

WHAT IT DOES

What clone_instrument does on Redcap

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

WHY IT NEEDS A POLICY

Why clone_instrument needs a policy

Cloning an instrument creates a new copy of a research data collection form. This is a reversible Write operation—it modifies the project structure by adding new data structures, but the original remains and the action can be undone by deleting the cloned instrument. Not Destructive because the original is not removed and the action is reversible. Not Execute because it does not run arbitrary code.

From the tool's definition Tool name 'clone_instrument' combined with sibling tools like 'add_instrument' and 'delete_instrument' on a REDCap data management server. The function copies/duplicates an existing instrument (questionnaire/form), which creates new data structures reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clone_instrument Rate-limited

clone_instrument 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": {
    "clone_instrument": {
      "limits": [
        {
          "counter": "clone_instrument_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 Redcap, so you can run agents against it safely.

FAQ

Questions about clone_instrument

What does the clone_instrument tool do? +

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

How do I enforce a policy on clone_instrument? +

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

What risk level is clone_instrument? +

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

Can I rate-limit clone_instrument? +

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

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

clone_instrument is provided by the Redcap MCP server (msicilia/mcp-server-redcap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.