stepfun_text2speech · StepFun MCP: Risk & Policy

WHAT IT DOES

What stepfun_text2speech does on StepFunMCP

AI agents invoke stepfun_text2speech to trigger actions in StepFunMCP. 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 stepfun_text2speech needs a policy

This tool calls an external TTS API and generates an audio file/URL, which constitutes triggering an external operation with side effects beyond simple data retrieval. It's not purely Read since it creates a new artifact, and it's not Write in the traditional sense (no user data store is modified). Execute best captures the external API invocation and file generation behavior.

From the tool's definition 调用 StepFun 语音合成（TTS）接口 — triggers an external API call to synthesize speech; Returns: 返回音频文件路径或URL — produces an output file or URL as a side effect

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stepfun_text2speech Rate-limited

stepfun_text2speech 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": {
    "stepfun_text2speech": {
      "limits": [
        {
          "counter": "stepfun_text2speech_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 StepFunMCP, so you can run agents against it safely.

FAQ

Questions about stepfun_text2speech

What does the stepfun_text2speech tool do? +

调用 StepFun 语音合成（TTS）接口。\nArgs:\n text (str): 要合成的文本\n voice (str, optional): 声音类型，默认 cixingnansheng。\n model (str, optional): 模型名称，默认 step-tts-mini。\nReturns:\n TextContent: 返回音频文件路径或URL. It is categorised as a Execute tool in the StepFunMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stepfun_text2speech? +

Register the StepFun MCP server in PolicyLayer and add a rule for stepfun_text2speech: 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 StepFunMCP. Nothing to install.

What risk level is stepfun_text2speech? +

stepfun_text2speech is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit stepfun_text2speech? +

Yes. Add a rate_limit block to the stepfun_text2speech 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 stepfun_text2speech completely? +

Set action: deny in the PolicyLayer policy for stepfun_text2speech. 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 stepfun_text2speech? +

stepfun_text2speech is provided by the StepFun MCP server (weidafeng/stepfunmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.