Get a sample of data from a table
AI agents call get_table_sample to retrieve information from DataPilot MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a Snowflake table without any capability to modify, delete, or execute operations. It is a non-destructive query operation with minimal side effects, fitting squarely within the Read category. The severity is low as sampling data poses minimal risk even if misused by an agent—it cannot alter data, trigger financial transactions, or execute arbitrary code.
From the tool's definition Tool name 'get_table_sample' and description 'Get a sample of data from a table' indicate data retrieval without modification. The action is a read-only query operation that retrieves a subset of rows for inspection.
Attacks that exploit this kind of access
Get a sample of data from a table. It is categorised as a Read tool in the DataPilot MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DataPilot MCP Server MCP server in PolicyLayer and add a rule for get_table_sample: 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 DataPilot MCP Server. Nothing to install.
get_table_sample 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 get_table_sample 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 get_table_sample. 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.
get_table_sample is provided by the DataPilot MCP Server MCP server (rickyb30/datapilot-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 →