AI agents call explain_table to retrieve information from Mcp Windows without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries and returns information about database table structure. It has no side effects, cannot modify data, and poses minimal risk even if misused by an AI agent. The severity is low because it only exposes non-sensitive schema metadata that would typically be available to any database user with basic access.
From the tool's definition Tool description states 'Explain table structure (alias for DESCRIBE)' - DESCRIBE is a SQL query command that retrieves metadata about table schemas without modifying data.
Documented attack patterns abuse exactly the kind of access explain_table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Windows, and nothing reaches the server without passing your rules. This is the rule we recommend for explain_table:
{
"version": "1",
"default": "deny",
"tools": {
"explain_table": {}
}
}explain_table 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.
Explain table structure (alias for DESCRIBE). It is categorised as a Read tool in the Mcp Windows MCP Server, which means it retrieves data without modifying state.
Register the Mcp Windows MCP server in PolicyLayer and add a rule for explain_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 Mcp Windows. Nothing to install.
explain_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 explain_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 explain_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.
explain_table is provided by the Mcp Windows MCP server (mukul975/mcp-windows-automation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 441 Mcp Windows tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
441 Mcp Windows tools catalogued and risk-classified — across an index of 42,500+ MCP servers.