AI agents use save_mxd 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 modifies data reversibly by saving an ArcMap document. The .mxd file is updated with any changes made in the current session. While it writes to the filesystem, it is not destructive (not irreversible deletion) nor does it execute arbitrary code or move money.
From the tool's definition Tool description: 'Guarda el documento .mxd abierto en su ruta actual' (Saves the open .mxd document in its current path). The tool saves/writes a file to disk, modifying the existing .mxd document.
Attacks that exploit this kind of access
Guarda el documento .mxd abierto en su ruta actual. Devuelve la ruta guardada. 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: 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 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 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. 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 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 →