flc_describe
AI agents call flc_describe 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 'describe' verb strongly implies querying/retrieving metadata about a feature layer collection (flc). Describe operations are non-destructive, read-only actions. Confidence is moderate (0.6) due to the empty description, which prevents full verification of the tool's actual behavior, but the naming convention and context within a feature layer management API support classification as Read.
From the tool's definition Tool name 'flc_describe' suggests a describe operation on feature layer collections, which typically retrieves metadata and schema information without modifying data. No description provided to confirm.
Attacks that exploit this kind of access
flc_describe. 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 flc_describe: 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.
flc_describe 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 flc_describe 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 flc_describe. 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.
flc_describe 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 →