使用火山方舟 Seedream 模型进行图生图(Ark-only)
AI agents invoke image-to-image to trigger actions in Seedream/Seedance MCP Server. 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.
This tool invokes an external AI model API (Volcengine Ark) to process an input image and produce a new image. It is not a simple read/query operation, nor does it delete data. It executes an external operation (image generation/transformation) whose output depends on the input arguments, placing it in the Execute category.
From the tool's definition 图生图 (image-to-image) — triggers external API call to Volcengine's Ark API to generate/transform images using the Seedream model
Attacks that exploit this kind of access
使用火山方舟 Seedream 模型进行图生图(Ark-only). It is categorised as a Execute tool in the Seedream/Seedance MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Seedream/Seedance MCP Server MCP server in PolicyLayer and add a rule for image-to-image: 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 Seedream/Seedance MCP Server. Nothing to install.
image-to-image is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the image-to-image 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 image-to-image. 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.
image-to-image is provided by the Seedream/Seedance MCP Server MCP server (nsmao-com/seedream-mcp). 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 →