create_credential · N8n MCP: Risk & Policy

WHAT IT DOES

What create_credential does on N8n

AI agents use create_credential to create or update resources in N8n — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N8n environment.

WHY IT NEEDS A POLICY

Why create_credential needs a policy

Classified as Write rather than Read because it creates/persists new data (a credential) with reversible effects. Severity is high because credentials are sensitive security artifacts; misconfigured or malicious credentials could be leveraged to compromise connected services and steal data. However, it does not move money (Financial), execute arbitrary code (Execute), or permanently destroy data (Destructive).

From the tool's definition Tool creates a new credential object. Description states 'Create a new credential.' Credentials in n8n are authentication artifacts that store sensitive data like API keys, passwords, and tokens used to authenticate with external services.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_credential Rate-limited

create_credential 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": {
    "create_credential": {
      "limits": [
        {
          "counter": "create_credential_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 N8n, so you can run agents against it safely.

FAQ

Questions about create_credential

What does the create_credential tool do? +

Create a new credential. Use get_credential_schema to discover required fields first. It is categorised as a Write tool in the N8n MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_credential? +

Register the N8n MCP server in PolicyLayer and add a rule for create_credential: 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 N8n. Nothing to install.

What risk level is create_credential? +

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

Can I rate-limit create_credential? +

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

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

create_credential is provided by the N8n MCP server (siddharth0903/n8n-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.