AI agents call mcp_preview_data to retrieve information from Mcpql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays a preview of existing data from a database table. It has no capability to modify, delete, or execute operations—only to query and present data. The optional filters are for scoping the read operation, not for mutation. This is a classic Read operation with minimal blast radius even if misused by an AI agent.
From the tool's definition Tool name 'mcp_preview_data' and description 'Get a preview of data from a SQL Server table with optional filters' both indicate read-only retrieval of table data.
Attacks that exploit this kind of access
Get a preview of data from a SQL Server table with optional filters. It is categorised as a Read tool in the Mcpql MCP Server, which means it retrieves data without modifying state.
Register the Mcpql MCP server in PolicyLayer and add a rule for mcp_preview_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 Mcpql. Nothing to install.
mcp_preview_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 mcp_preview_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 mcp_preview_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.
mcp_preview_data is provided by the Mcpql MCP server (mcpql). 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 →