AI agents call query_table to retrieve information from Pl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries data from a table and returns results without modifying, deleting, or executing operations. It is a read-only operation with minimal blast radius if misused by an AI agent, as it only exposes data already present in the PTable.
From the tool's definition Tool description states 'Query data from a PTable. Returns rows as arrays of values.' The verb 'query' and 'returns' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Query data from a PTable. Returns rows as arrays of values. Use get_block_outputs first to find the PTable handle. It is categorised as a Read tool in the Pl MCP Server, which means it retrieves data without modifying state.
Register the Pl MCP server in PolicyLayer and add a rule for query_table: 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 Pl. Nothing to install.
query_table 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_table 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_table. 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_table is provided by the Pl MCP server (@milaboratories/pl-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 →