AI agents call pymdu_building_to_image to retrieve information from Pymdu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and transforms existing data (a GeoDataFrame) into a visual representation format. It performs no create, modify, delete, execute, or financial operations. The visualization is a read-only operation that does not alter the source data or trigger external code execution. Low severity because misuse simply produces unwanted image output without broader system impact.
From the tool's definition Tool performs conversion/visualization of GeoDataFrame data to an image format. Description explicitly states 'Convert a GeoDataFrame to an image visualization' with no modification or deletion of underlying data.
Attacks that exploit this kind of access
Convert a GeoDataFrame to an image visualization. It is categorised as a Read tool in the Pymdu MCP Server, which means it retrieves data without modifying state.
Register the Pymdu MCP server in PolicyLayer and add a rule for pymdu_building_to_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 Pymdu. Nothing to install.
pymdu_building_to_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 pymdu_building_to_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 pymdu_building_to_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.
pymdu_building_to_image is provided by the Pymdu MCP server (rupeelab17/mcp_pymdu). 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 →