AI agents call ReadImage to retrieve information from Mcp Wcgw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads image file data for viewing or processing purposes. It performs no writes, deletes, executions, or other side effects. Even in the context of a shell/file editing server with powerful capabilities, this specific tool is narrowly scoped to reading image content. Severity is low because image data retrieval poses minimal risk of misuse compared to command execution or file destruction.
From the tool's definition Tool name is 'ReadImage' and description states it will 'Read image files for display/processing' — a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access ReadImage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Wcgw, and nothing reaches the server without passing your rules. This is the rule we recommend for ReadImage:
{
"version": "1",
"default": "deny",
"tools": {
"ReadImage": {}
}
}ReadImage is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read image files for display/processing. It is categorised as a Read tool in the Mcp Wcgw MCP Server, which means it retrieves data without modifying state.
Register the Mcp Wcgw MCP server in PolicyLayer and add a rule for ReadImage: 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 Wcgw. Nothing to install.
ReadImage 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 ReadImage 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 ReadImage. 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.
ReadImage is provided by the Mcp Wcgw MCP server (rusiaaman/wcgw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Mcp Wcgw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Mcp Wcgw tools catalogued and risk-classified — across an index of 42,500+ MCP servers.