执行SQL查询并返回结果集（仅支持SELECT语句）
AI agents call query_sql to retrieve information from Jewei MSSQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it only supports SELECT statements, meaning it retrieves data without side effects. However, there is moderate risk because SELECT queries on sensitive databases can expose confidential data, and the enforcement of the SELECT-only restriction depends on server-side validation. Severity is medium due to potential data exfiltration if misused.
From the tool's definition 执行SQL查询并返回结果集（仅支持SELECT语句） — 'only supports SELECT statements' and 'returns result set'
Attacks that exploit this kind of access
执行SQL查询并返回结果集（仅支持SELECT语句）. It is categorised as a Read tool in the Jewei MSSQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jewei MSSQL MCP Server MCP server in PolicyLayer and add a rule for query_sql: 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 Jewei MSSQL MCP Server. Nothing to install.
query_sql 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 query_sql 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 query_sql. 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.
query_sql is provided by the Jewei MSSQL MCP Server MCP server (jeweis/jewei-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 →