AI agents invoke execute_arcpy 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 arbitrary Python/arcpy code in the context of a live ArcMap application. arcpy is Esri's Python API for controlling ArcGIS/ArcMap operations. Arbitrary code execution is inherently an Execute-category risk. The blast radius is high because arcpy commands could modify data, delete features, corrupt maps, or trigger unintended geographic data operations depending on what code is executed.
From the tool's definition Tool name 'execute_arcpy' combined with server description stating it 'allows AI agents to control a live ArcMap session via arcpy' and 'execute_script' listed as an Execute example in classification rules.
Attacks that exploit this kind of access
execute_arcpy. 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 execute_arcpy: 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.
execute_arcpy 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 execute_arcpy 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 execute_arcpy. 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.
execute_arcpy 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 →