获取支持的视频格式和编码
AI agents call getSupportedFormats to retrieve information from Video Clip MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns static configuration data about supported formats. This is a standard read-only information retrieval operation with no side effects, minimal blast radius, and no risk of data loss or unwanted execution.
From the tool's definition getSupportedFormats: retrieves a list of supported video formats and codecs ("获取支持的视频格式和编码" translates to "get supported video formats and encoding"). This is a query operation that returns metadata without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
获取支持的视频格式和编码. It is categorised as a Read tool in the Video Clip MCP MCP Server, which means it retrieves data without modifying state.
Register the Video Clip MCP server in PolicyLayer and add a rule for getSupportedFormats: 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 Video Clip MCP. Nothing to install.
getSupportedFormats 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 getSupportedFormats 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 getSupportedFormats. 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.
getSupportedFormats is provided by the Video Clip MCP server (pickstar-2002/video-clip-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 →