AI agents call list_portal_categories to retrieve information from Socrata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely retrieves and displays metadata about available dataset categories on a portal. It has no side effects, does not execute code, does not modify or delete data, and does not involve financial transactions. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'list_portal_categories' and description states 'List dataset categories available on a specific Socrata portal.' The verb 'list' and the read-only nature of enumerating available categories indicates no data modification, deletion, or execution.
Attacks that exploit this kind of access
List dataset categories available on a specific Socrata portal. It is categorised as a Read tool in the Socrata MCP Server, which means it retrieves data without modifying state.
Register the Socrata MCP server in PolicyLayer and add a rule for list_portal_categories: 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 Socrata. Nothing to install.
list_portal_categories 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 list_portal_categories 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 list_portal_categories. 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.
list_portal_categories is provided by the Socrata MCP server (pathennessy/socrata-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 →