AI agents invoke contours to trigger actions in Arcmap. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a 3D Analyst geoprocessing operation (contour generation) via arcpy, which triggers an external computation and writes output files to disk. It is more than a simple Read, as it runs a spatial analysis function and produces new datasets. It falls under Execute as it triggers an external operation (arcpy geoprocessing), though it also has Write characteristics since it creates new layer files.
From the tool's definition 'Genera curvas de nivel desde un MDT (3D Analyst)' — generates contour lines from a DTM using ArcPy/3D Analyst, which runs a geoprocessing tool that creates new data on disk
Attacks that exploit this kind of access
Genera curvas de nivel desde un MDT (3D Analyst). intervalo = equidistancia. It is categorised as a Execute tool in the Arcmap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Arcmap MCP server in PolicyLayer and add a rule for contours: 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 Arcmap. Nothing to install.
contours is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the contours 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 contours. 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.
contours is provided by the Arcmap MCP server (pedralcg/arcmap-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 →