Retrieves a random sample of rows from the specified table in the Azure Data Explorer database. The sample_size parameter controls how many rows to return (default: 10).
AI agents call sample_table_data to retrieve information from Adx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data from an Azure Data Explorer table with no side effects. It performs data retrieval only, with a bounded sample size parameter. The operation is non-destructive and reversible. No code execution, financial transactions, or data modification occurs. This aligns with the 'Read' category for tools that retrieve or query data without side effects.
From the tool's definition Tool description states it 'Retrieves a random sample of rows from the specified table' — a pure read operation that returns data without modification, creation, or deletion.
Documented attack patterns abuse exactly the kind of access sample_table_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adx, and nothing reaches the server without passing your rules. This is the rule we recommend for sample_table_data:
{
"version": "1",
"default": "deny",
"tools": {
"sample_table_data": {}
}
}sample_table_data is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieves a random sample of rows from the specified table in the Azure Data Explorer database. The sample_size parameter controls how many rows to return (default: 10). It is categorised as a Read tool in the Adx MCP Server, which means it retrieves data without modifying state.
Register the Adx MCP server in PolicyLayer and add a rule for sample_table_data: 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 Adx. Nothing to install.
sample_table_data 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 sample_table_data 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 sample_table_data. 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.
sample_table_data is provided by the Adx MCP server (pab1it0/adx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Adx tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Adx tools catalogued and risk-classified — across an index of 42,500+ MCP servers.