AI agents call list_venues to retrieve information from Palate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays venue information from the Palate Network without creating, modifying, or deleting any data. It is a straightforward data retrieval operation with minimal risk of misuse—an agent cannot cause harm by listing venues. Severity is low because the blast radius of misuse is negligible; the worst outcome would be an agent repeatedly querying the list.
From the tool's definition Tool name 'list_venues' and description 'List all venues' indicate retrieval of data. The verb 'list' and the operation of displaying existing venues with their scores and review counts constitute a read-only query with no side effects.
Attacks that exploit this kind of access
List all venues on the Palate Network with scores and review counts. It is categorised as a Read tool in the Palate MCP Server, which means it retrieves data without modifying state.
Register the Palate MCP server in PolicyLayer and add a rule for list_venues: 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 Palate. Nothing to install.
list_venues 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_venues 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_venues. 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_venues is provided by the Palate MCP server (palate-mcp-server). 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 →