AI agents call caption_image to retrieve information from Videoseek without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes image data to generate captions or descriptions. It has no side effects—it does not create, modify, delete, or execute external operations. The operation is non-destructive, non-financial, and produces informational output only.
From the tool's definition The tool performs image analysis using AI vision from a URL. The description uses 'Analyze' which indicates a read-only operation that retrieves and processes visual data without creating, modifying, or deleting any resources.
Attacks that exploit this kind of access
Analyze an image from URL using AI vision. It is categorised as a Read tool in the Videoseek MCP Server, which means it retrieves data without modifying state.
Register the Videoseek MCP server in PolicyLayer and add a rule for caption_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 Videoseek. Nothing to install.
caption_image 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 caption_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 caption_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.
caption_image is provided by the Videoseek MCP server (kennyzheng-builds/videoseek-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 →