图片处理(组合操作,支持多种处理参数)
AI agents invoke tos_image_process to trigger actions in TOS 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 performs image processing operations (resize, crop, watermark, format conversion, etc.) on objects in TOS storage. It executes transformations on existing data rather than purely reading or writing raw data. It may produce new derived objects or modify stored images depending on implementation. Since it 'executes' processing pipelines with combined parameters, Execute is the most appropriate category.
From the tool's definition 图片处理(组合操作,支持多种处理参数) — 'image processing with combined operations and multiple processing parameters'
Attacks that exploit this kind of access
图片处理(组合操作,支持多种处理参数). It is categorised as a Execute tool in the TOS MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TOS MCP Server MCP server in PolicyLayer and add a rule for tos_image_process: 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 TOS MCP Server. Nothing to install.
tos_image_process 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 tos_image_process 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 tos_image_process. 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.
tos_image_process is provided by the TOS MCP Server MCP server (jneless/tos-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 →