webscene_get
AI agents call webscene_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.
The 'get' suffix and absence of modify/delete keywords indicate a read operation. Classified as Read rather than Execute because it appears to be a data retrieval endpoint. Severity is medium rather than low because web scenes in ArcGIS systems may contain sensitive geospatial or organizational data, and unauthorized access could expose business intelligence or restricted geographic information.
From the tool's definition Tool name 'webscene_get' indicates a retrieval operation ('get'). No description provided, but naming convention and context within an ArcGIS MCP server managing items, features, and geoprocessing suggest this retrieves web scene metadata or data.
Attacks that exploit this kind of access
webscene_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 webscene_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.
webscene_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 webscene_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 webscene_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.
webscene_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 →