list_categories
Enumerate the full category tree for browsing GallanDigital's marketplace. Read-only, no authentication required (public endpoint, IP rate-limited), no parameters. Returns an array of categories, each with id, name, slug, description, parent_id, level, and display_order. Use first when browsing b...
This record as markdown: /tools/com-gallandigital-marketplace/list-categories.md
What list_categories does on Marketplace
AI agents call list_categories to retrieve information from Marketplace without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_categories is rated Low
This tool retrieves and lists public marketplace category metadata. It performs no modifications, deletions, or external executions. The absence of authentication and explicit 'read-only' designation confirm it is a simple enumeration endpoint. Low severity because exposure of category structure is unlikely to cause harm even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Read-only', 'no authentication required', and it 'Enumerate[s] the full category tree' and 'Returns an array of categories'. These are all characteristics of a data retrieval operation with no side effects.
Attacks that exploit this kind of access
The rule that runs list_categories safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Marketplace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_categories, this is the rule to start with:
list_categories is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Marketplace, apply this rule, and every list_categories call is checked against it from then on.
Questions about list_categories
Enumerate the full category tree for browsing GallanDigital's marketplace. Read-only, no authentication required (public endpoint, IP rate-limited), no parameters. Returns an array of categories, each with id, name, slug, description, parent_id, level, and display_order. Use first when browsing by category rather than searching by keyword, or to get valid category_slug values for search. It is categorised as a Read tool in the Marketplace MCP Server, which means it retrieves data without modifying state.
Register the Marketplace MCP server in PolicyLayer and add a rule for list_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 Marketplace. Nothing to install.
list_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_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_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_categories is provided by the Marketplace MCP server (https://gallandigital.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Marketplace, and thousands of servers like it.
This server
Across the catalogue