获取视频信息
AI agents call tos_video_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 video metadata/information from object storage. It performs a read-only query operation with no side effects, no data modification, no code execution, and no deletion. The minimal severity reflects that metadata retrieval poses low risk even if an AI agent accesses it unprompted, as it only exposes existing information without enabling destructive or write operations.
From the tool's definition Tool name 'tos_video_info' and description '获取视频信息' (get video information) indicate retrieval of metadata about video objects stored in TOS without modification.
Attacks that exploit this kind of access
获取视频信息. 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_video_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_video_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_video_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_video_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_video_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 →