Searches for a term in the common text fields of a table using a LIKE query.
AI agents call search_records_by_text to retrieve information from Snow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a text search operation using LIKE pattern matching, which is a standard database query that retrieves data without side effects. It does not create, modify, delete, or execute any operations—it only returns matching records. This is a typical Read category operation. Severity is low because search operations have minimal blast radius and cannot cause harm to system state or data integrity.
From the tool's definition Tool description states it 'Searches for a term in the common text fields of a table using a LIKE query.' This is a read-only query operation with no modification, deletion, or execution of external code.
Documented attack patterns abuse exactly the kind of access search_records_by_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Snow, and nothing reaches the server without passing your rules. This is the rule we recommend for search_records_by_text:
{
"version": "1",
"default": "deny",
"tools": {
"search_records_by_text": {}
}
} search_records_by_text is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches for a term in the common text fields of a table using a LIKE query. It is categorised as a Read tool in the Snow MCP Server, which means it retrieves data without modifying state.
Register the Snow MCP server in PolicyLayer and add a rule for search_records_by_text: 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 Snow. Nothing to install.
search_records_by_text 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 search_records_by_text 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 search_records_by_text. 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.
search_records_by_text is provided by the Snow MCP server (shunyaai/snow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Snow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
88 Snow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.