create_secret · Vaulted MCP Server MCP: Risk & Policy

WHAT IT DOES

What create_secret does on Vaulted MCP Server

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

WHY IT NEEDS A POLICY

Why create_secret needs a policy

The tool writes/stores data (creating encrypted secrets and shareable links) but is not destructive (self-destructing is automatic, not user-initiated deletion), not financial, and not arbitrary code execution. It is reversible in principle (secrets can be regenerated).

From the tool's definition Tool creates a secure link for sharing sensitive data; description states it 'Create[s] a secure, self-destructing link' and stores secrets with encryption. This is data creation/storage, albeit with security safeguards (E2E encryption, self-destructing).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_secret Rate-limited

create_secret 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_secret": {
      "limits": [
        {
          "counter": "create_secret_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 Vaulted MCP Server, so you can run agents against it safely.

FAQ

Questions about create_secret

What does the create_secret tool do? +

Create a secure, self-destructing link for sharing sensitive data like passwords, API keys, or credentials. The secret is encrypted end-to-end — the server never sees plaintext. Supports reading secrets from environment variables, files, or .env files without exposing them in the conversation. Optionally provide a label to identify the secret in your history. It is categorised as a Write tool in the Vaulted MCP Server 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_secret? +

Register the Vaulted MCP Server MCP server in PolicyLayer and add a rule for create_secret: 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 Vaulted MCP Server. Nothing to install.

What risk level is create_secret? +

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

Can I rate-limit create_secret? +

Yes. Add a rate_limit block to the create_secret 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_secret completely? +

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

create_secret is provided by the Vaulted MCP Server MCP server (vaulted-fyi/vaulted-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.