调用 StepFun 文生图模型生成图片。\nArgs:\n prompt (str): 文本描述\n model (str, optional): 模型名称，默认 step-1x-medium。\n n (int, optional): 生成图片数量，默认1。\n size (str, optional): 图片尺寸。\n seed (int, optional): 随机种子。\nReturns:\n TextContent: 图片存储的文件路径
AI agents call stepfun_text2img to retrieve information from StepFunMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though stepfun_text2img only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
调用 StepFun 文生图模型生成图片。\nArgs:\n prompt (str): 文本描述\n model (str, optional): 模型名称，默认 step-1x-medium。\n n (int, optional): 生成图片数量，默认1。\n size (str, optional): 图片尺寸。\n seed (int, optional): 随机种子。\nReturns:\n TextContent: 图片存储的文件路径. It is categorised as a Read tool in the StepFunMCP MCP Server, which means it retrieves data without modifying state.
Register the StepFun MCP server in PolicyLayer and add a rule for stepfun_text2img: 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.
stepfun_text2img is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the stepfun_text2img 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.
Set action: deny in the PolicyLayer policy for stepfun_text2img. 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.
stepfun_text2img 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →