AI agents use repair_data_source 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 modifies the data source/workspace reference of a layer, which is a reversible write operation (the old path can be restored). However, it has high severity because remapping data sources in a live ArcMap session could break layer connections or redirect analysis to incorrect datasets, potentially causing significant downstream errors. Confidence is slightly reduced because the description is truncated.
From the tool's definition 'Reapunta la fuente de una capa sustituyendo su workspace' (re-points the source of a layer by substituting its workspace)
Attacks that exploit this kind of access
Reapunta la fuente de una capa sustituyendo su workspace (ruta_antigua ->. 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 repair_data_source: 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.
repair_data_source 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 repair_data_source 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 repair_data_source. 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.
repair_data_source 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 →