mask_text · TinyFn MCP: Risk & Policy

WHAT IT DOES

What mask_text does on TinyFn

AI agents invoke mask_text to trigger actions in TinyFn. 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.

PARAMETERS

Parameter	Type	Required	Description
`end`	integer	—	Characters to keep at end
`text`	string	Yes	Text to mask
`start`	integer	—	Characters to keep at start
`mask_char`	string	—	Masking character

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why mask_text needs a policy

mask_text triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mask_text Rate-limited

mask_text 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": {
    "mask_text": {
      "limits": [
        {
          "counter": "mask_text_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 TinyFn, so you can run agents against it safely.

FAQ

Questions about mask_text

What does the mask_text tool do? +

Mask text, keeping only start/end characters visible. It is categorised as a Execute tool in the TinyFn MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does mask_text accept? +

mask_text accepts 4 parameters: end, text, start, mask_char. Required: text. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on mask_text? +

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

What risk level is mask_text? +

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

Can I rate-limit mask_text? +

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

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

mask_text is provided by the TinyFn MCP server (https://api.tinyfn.io/mcp/all/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.