fl_related_records
AI agents call fl_related_records 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.
Feature layer queries that retrieve related records are read-only operations with no side effects. The tool name pattern 'fl_*' (feature layer prefix) and the semantic meaning of 'related_records' indicate data retrieval rather than modification, deletion, or execution of arbitrary code. Without evidence of write, delete, or execute capabilities, this defaults to Read category with low blast radius.
From the tool's definition Tool name 'fl_related_records' suggests querying related records from a feature layer (fl_), a read operation. The empty description limits certainty, but feature layer record retrieval is typically a non-destructive query operation.
Attacks that exploit this kind of access
fl_related_records. 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 fl_related_records: 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.
fl_related_records 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 fl_related_records 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 fl_related_records. 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.
fl_related_records 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 →