获取图片信息
AI agents call tos_image_info to retrieve information from TOS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries image metadata from the object storage service. It has no side effects and does not create, modify, execute, delete, or move data. It is a read-only operation consistent with 'get' semantics. Severity is low because querying image metadata has minimal blast radius even if invoked incorrectly by an AI agent.
From the tool's definition Tool name 'tos_image_info' with description '获取图片信息' (retrieve image information). The tool queries metadata about images stored in TOS without modifying, executing operations on, or deleting data.
Attacks that exploit this kind of access
获取图片信息. It is categorised as a Read tool in the TOS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TOS MCP Server MCP server in PolicyLayer and add a rule for tos_image_info: 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_info 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 tos_image_info 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_info. 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_info 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 →