Retrieve images by id or key. Optionally include base64 data.
AI agents call image-get to retrieve information from MCP Index Notes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/fetches image data without creating, modifying, or deleting anything. It is a simple GET operation that queries stored images, making it a Read category tool with low severity as there is minimal blast radius from misuse—an agent could only access images, not alter system state or cause data loss.
From the tool's definition Tool name is 'image-get' and description states 'Retrieve images by id or key.' The verb 'retrieve' and the absence of any modification or deletion capability clearly indicate a read operation with no side effects.
Attacks that exploit this kind of access
Retrieve images by id or key. Optionally include base64 data. It is categorised as a Read tool in the MCP Index Notes MCP Server, which means it retrieves data without modifying state.
Register the MCP Index Notes MCP server in PolicyLayer and add a rule for image-get: 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 MCP Index Notes. Nothing to install.
image-get 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 image-get 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 image-get. 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.
image-get is provided by the MCP Index Notes MCP server (vjsr007/mcp-index-notes). 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 →