creds_add · ML Lab MCP: Risk & Policy

WHAT IT DOES

What creds_add does on ML Lab MCP

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

WHY IT NEEDS A POLICY

Why creds_add needs a policy

While credential storage involves sensitive information, the tool performs a Write operation (create/update) rather than Execute or Destructive. It is not Financial. However, severity is elevated to 'high' because misuse could allow an AI agent to inject false or malicious credentials for cloud providers (Lambda Labs, RunPod, Mistral, Together AI, OpenAI, SSH), potentially leading to unauthorized API access,…

From the tool's definition Tool description states 'Add or update credentials for a provider' - this directly creates or modifies credential data in what is evidently a credential vault (per sibling tool 'creds_create_vault').

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

creds_add Rate-limited

creds_add 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": {
    "creds_add": {
      "limits": [
        {
          "counter": "creds_add_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 ML Lab MCP, so you can run agents against it safely.

FAQ

Questions about creds_add

What does the creds_add tool do? +

Add or update credentials for a provider. It is categorised as a Write tool in the ML Lab 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 creds_add? +

Register the ML Lab MCP server in PolicyLayer and add a rule for creds_add: 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 ML Lab MCP. Nothing to install.

What risk level is creds_add? +

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

Can I rate-limit creds_add? +

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

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

creds_add is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.