Generate a safe read-only MSSQL SELECT from instruction via Gemini, validate, execute, and return rows.
AI agents call ai_query_mssql to retrieve information from LINE Bot MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is classified as Read because it performs SELECT queries against MSSQL databases with explicit read-only constraints. While it uses AI (Gemini) to generate SQL, the stated safety mechanism ('safe read-only') and the limitation to SELECT statements prevent write, delete, or execute operations.
From the tool's definition Tool description states 'read-only MSSQL SELECT', explicitly limiting to query operations without data modification or deletion. Name 'ai_query_mssql' and description 'Generate a safe read-only MSSQL SELECT...
Attacks that exploit this kind of access
Generate a safe read-only MSSQL SELECT from instruction via Gemini, validate, execute, and return rows. It is categorised as a Read tool in the LINE Bot MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LINE Bot MCP Server MCP server in PolicyLayer and add a rule for ai_query_mssql: 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 LINE Bot MCP Server. Nothing to install.
ai_query_mssql 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 ai_query_mssql 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 ai_query_mssql. 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.
ai_query_mssql is provided by the LINE Bot MCP Server MCP server (tndfame/mcp_management). 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 →