preview the first 10 rows of a table
AI agents call preview_table to retrieve information from Doris-MCP-Lite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves sample data from a table without side effects. It is a simple query operation that fetches and displays data only—no creation, modification, deletion, or execution of arbitrary operations. The read-only constraint of the server and the preview-only nature of the operation (10 rows maximum) minimize risk of harm.
From the tool's definition Tool 'preview_table' returns 'the first 10 rows of a table' with no modification capability. The server is explicitly described as supporting 'read-only SQL queries' and 'data analysis'.
Attacks that exploit this kind of access
preview the first 10 rows of a table. It is categorised as a Read tool in the Doris-MCP-Lite MCP Server, which means it retrieves data without modifying state.
Register the Doris-MCP-Lite MCP server in PolicyLayer and add a rule for preview_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 Doris-MCP-Lite. Nothing to install.
preview_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 preview_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 preview_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.
preview_table is provided by the Doris-MCP-Lite MCP server (nomotok/doris-mcp-lite). 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 →