geocode_suggest
AI agents call geocode_suggest 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.
Geocoding suggestion tools typically retrieve candidate locations matching partial input (read-only). No evidence of data modification, deletion, code execution, or financial operations. The low confidence reflects the missing description, but the tool name and ArcGIS server context strongly indicate a safe read operation with minimal blast radius if misused.
From the tool's definition Tool name 'geocode_suggest' suggests autocomplete/suggestion functionality for geocoding (address lookup). Based on ArcGIS patterns, this likely returns location suggestions without modifying data.
Attacks that exploit this kind of access
geocode_suggest. 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 geocode_suggest: 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.
geocode_suggest 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 geocode_suggest 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 geocode_suggest. 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.
geocode_suggest 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 →