alt_text
AI agents call alt_text to retrieve information from Computer Vision MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to generate alternative text descriptions for images, which is a read-only operation that retrieves or generates information about image content without modifying data or triggering external operations. The lack of a description lowers confidence slightly, but the clear context from sibling tools and server purpose strongly indicates this is a passive analysis tool.
From the tool's definition Tool name 'alt_text' and sibling tools 'caption_image', 'dense_caption', 'image_metadata' all perform image analysis and description operations.
Attacks that exploit this kind of access
alt_text. It is categorised as a Read tool in the Computer Vision MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Computer Vision MCP Server MCP server in PolicyLayer and add a rule for alt_text: 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 Computer Vision MCP Server. Nothing to install.
alt_text 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 alt_text 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 alt_text. 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.
alt_text is provided by the Computer Vision MCP Server MCP server (samhains/cv-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 →