AI agents invoke run_geoprocessing 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.
Geoprocessing operations can perform complex spatial transformations, modify data, and trigger external geospatial operations. Without a description to constrain scope, and given the arcpy execution context, this tool should be classified as Execute rather than Write because geoprocessing tools often have irreversible effects (e.g., spatial transformations, rasterization, feature generalization) and side effects…
From the tool's definition Tool named 'run_geoprocessing' on an ArcMap MCP server where sibling tools include 'execute_arcpy' and the server description explicitly mentions 'allows AI agents to control a live ArcMap session via arcpy'.
Attacks that exploit this kind of access
run_geoprocessing. 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 run_geoprocessing: 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.
run_geoprocessing 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 run_geoprocessing 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 run_geoprocessing. 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.
run_geoprocessing 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 →