AI agents call query_network 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.
The tool performs a read-only query operation that retrieves and ranks venue data based on natural language input. It has no side effects, does not execute code or commands, does not modify data, and does not cause financial transactions.
From the tool's definition Tool description states it 'Ask[s] the Palate Network a natural-language question and get ranked venue recommendations' — a pure query/retrieval operation with no modification or execution capabilities.
Attacks that exploit this kind of access
Ask the Palate Network a natural-language question and get ranked venue recommendations. Requires at least 2 review contributions to unlock. 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 query_network: 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.
query_network 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 query_network 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 query_network. 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.
query_network 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 →