Execute a SQL query (SELECT only by default) against the database.
AI agents call mssql_query to retrieve information from MSSQL Database MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is designed for read-only SQL queries (SELECT statements) by default, placing it in the Read category. However, the phrase 'by default' implies there may be configurations or edge cases where non-SELECT statements could be permitted, which introduces some uncertainty and warrants a medium severity.
From the tool's definition 'Execute a SQL query (SELECT only by default)' — the tool is described as SELECT-only by default, indicating read operations
Attacks that exploit this kind of access
Execute a SQL query (SELECT only by default) against the database. It is categorised as a Read tool in the MSSQL Database MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MSSQL Database MCP Server MCP server in PolicyLayer and add a rule for mssql_query: 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 MSSQL Database MCP Server. Nothing to install.
mssql_query 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 mssql_query 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 mssql_query. 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.
mssql_query is provided by the MSSQL Database MCP Server MCP server (vpro1032/mssql-mcp-server). 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 →