Execute a read-only SELECT query
AI agents invoke mssql_query to trigger actions in Enhanced MCP MSSQL Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Although restricted to SELECT statements, executing arbitrary SQL queries against a production database carries high risk. A malicious or poorly formed query could expose sensitive data, cause denial of service through expensive queries, or be used for SQL injection if input sanitization is inadequate. The server description mentions 'production environments', raising the blast radius.
From the tool's definition 'Execute a read-only SELECT query' — the tool actively executes SQL queries against a production database
Attacks that exploit this kind of access
Execute a read-only SELECT query. It is categorised as a Execute tool in the Enhanced MCP MSSQL Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Enhanced MCP MSSQL 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 Enhanced MCP MSSQL Server. Nothing to install.
mssql_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 Enhanced MCP MSSQL Server MCP server (michaelyuwh/mcp-mssql-connector). 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 →