Execute a SELECT query.
AI agents call read_query to retrieve information from Snowflake 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 explicitly described as executing SELECT queries, which are read-only operations that retrieve data without modifying it. However, severity is medium because SELECT queries can expose sensitive data from Snowflake databases, and there is a slight risk that a crafted SELECT could invoke functions with side effects. The description is minimal but consistent with a read-only classification.
From the tool's definition Tool name 'read_query' and description 'Execute a SELECT query' indicate read-only data retrieval.
Attacks that exploit this kind of access
Execute a SELECT query. It is categorised as a Read tool in the Snowflake MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Snowflake MCP Server MCP server in PolicyLayer and add a rule for read_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 Snowflake MCP Server. Nothing to install.
read_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 read_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 read_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.
read_query is provided by the Snowflake MCP Server MCP server (tushar3006/mcp). 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 →