conduit_preview_transform · Conduit MCP: Risk & Policy

WHAT IT DOES

What conduit_preview_transform does on Conduit MCP

AI agents invoke conduit_preview_transform to trigger actions in Conduit MCP. 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 conduit_preview_transform needs a policy

This tool executes a transform (a computational operation) against provided input data. Execution of user-provided or configured transforms against arbitrary payloads falls into the Execute category because the actual effects depend on what the transform does — it could compute values, filter data, aggregate, or apply custom logic.

From the tool's definition Tool description states 'Preview a transform by running it against a sample payload' — this involves executing a transform operation against data, which is code/logic execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conduit_preview_transform Rate-limited

conduit_preview_transform 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": {
    "conduit_preview_transform": {
      "limits": [
        {
          "counter": "conduit_preview_transform_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 Conduit MCP, so you can run agents against it safely.

FAQ

Questions about conduit_preview_transform

What does the conduit_preview_transform tool do? +

Preview a transform by running it against a sample payload without persisting. Returns the transformed output and execution time. It is categorised as a Execute tool in the Conduit MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on conduit_preview_transform? +

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

What risk level is conduit_preview_transform? +

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

Can I rate-limit conduit_preview_transform? +

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

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

conduit_preview_transform is provided by the Conduit MCP server (useconduit/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.