AI agents use save_mxd_as to create or update resources in Arcmap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arcmap environment.
This tool creates or duplicates a file (ArcMap document) in a specified output location. File creation/duplication is a Write operation—it modifies the filesystem reversibly and does not delete or irreversibly alter existing data. The 'as' pattern and preservation of the original document confirm this is non-destructive duplication.
From the tool's definition Tool name 'save_mxd_as' and description 'Guarda una COPIA del .mxd en `salida`' (saves a copy of the .mxd to output) indicates creating/writing a new file.
Attacks that exploit this kind of access
Guarda una COPIA del .mxd en salida (no cambia el documento activo ni su ruta). It is categorised as a Write tool in the Arcmap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arcmap MCP server in PolicyLayer and add a rule for save_mxd_as: 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.
save_mxd_as is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_mxd_as 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 save_mxd_as. 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.
save_mxd_as 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 →