stepfun_chat_completion · StepFun MCP: Risk & Policy

WHAT IT DOES

What stepfun_chat_completion does on StepFunMCP

AI agents invoke stepfun_chat_completion 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_chat_completion needs a policy

This tool invokes an external AI model API to generate responses, which constitutes triggering an external operation. It is not a simple read of stored data but an active execution of a model inference call against a third-party service. The blast radius is medium as it consumes API credits and could generate harmful content if misused, but does not directly modify data or move money.

From the tool's definition 调用 StepFun 文本大模型生成聊天回复 (Calls StepFun text large model to generate chat replies)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stepfun_chat_completion Rate-limited

stepfun_chat_completion 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_chat_completion": {
      "limits": [
        {
          "counter": "stepfun_chat_completion_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_chat_completion

What does the stepfun_chat_completion tool do? +

调用 StepFun 文本大模型生成聊天回复。\nArgs:\n messages (list): 聊天历史，格式为 [{. 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_chat_completion? +

Register the StepFun MCP server in PolicyLayer and add a rule for stepfun_chat_completion: 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_chat_completion? +

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

Can I rate-limit stepfun_chat_completion? +

Yes. Add a rate_limit block to the stepfun_chat_completion 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_chat_completion completely? +

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

stepfun_chat_completion 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.