gp_run
AI agents invoke gp_run to trigger actions in ArcGIS MCP. 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 tools execute spatial analysis operations and external scripts whose effects depend on arguments. This fits Execute (runs code/triggers operations) rather than Read (would be gp_query or gp_list). High severity because misconfigured or malicious geoprocessing tasks could consume resources, corrupt spatial data, or trigger unintended side effects.
From the tool's definition Tool name 'gp_run' indicates geoprocessing execution; server context shows 'geoprocessing' is a core capability. Empty description is uninformative, but 'run' combined with geoprocessing context strongly suggests code/task execution.
Attacks that exploit this kind of access
gp_run. It is categorised as a Execute tool in the ArcGIS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ArcGIS MCP server in PolicyLayer and add a rule for gp_run: 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 ArcGIS MCP. Nothing to install.
gp_run 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 gp_run 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 gp_run. 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.
gp_run is provided by the ArcGIS MCP server (renemorenow/arcgis-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 →