gp_tool_help
AI agents call gp_tool_help to retrieve information from ArcGIS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates a read-only operation that retrieves help or documentation. No modification, execution, deletion, or financial action is implied. However, the empty description reduces confidence—if it actually executes geoprocessing operations or queries, classification might differ. Assuming standard help retrieval behavior, this falls under Read with low severity since it merely returns informational content.
From the tool's definition Tool name 'gp_tool_help' suggests retrieval of help documentation for geoprocessing tools. Description is empty, limiting certainty.
Attacks that exploit this kind of access
gp_tool_help. It is categorised as a Read tool in the ArcGIS MCP MCP Server, which means it retrieves data without modifying state.
Register the ArcGIS MCP server in PolicyLayer and add a rule for gp_tool_help: 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_tool_help is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gp_tool_help 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_tool_help. 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_tool_help 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 →