feature_get
AI agents call feature_get 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.
A 'feature_get' tool on a geospatial/GIS server most likely retrieves feature data from a feature layer without modifying it, placing it in the Read category. Severity is medium rather than low because the blast radius depends on what data is exposed—GIS features may contain sensitive geospatial, infrastructure, or property data.
From the tool's definition Tool name 'feature_get' indicates retrieval of feature data. Description is empty, but sibling tools on this server include feature layer queries and editing operations (feature_layer_queries/editing), and the server description explicitly mentions 'feature…
Attacks that exploit this kind of access
feature_get. 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 feature_get: 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.
feature_get 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 feature_get 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 feature_get. 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.
feature_get 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 →