List all schemas in a Snowflake database.
AI agents call snowflake_list_schemas to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves schema metadata from Snowflake without modifying, deleting, or executing anything. It is a straightforward informational query. Severity is low because listing schemas has minimal blast radius unless the schema names themselves are considered sensitive, but such queries are standard practice for database inspection.
From the tool's definition Tool name is 'snowflake_list_schemas' and description states 'List all schemas in a Snowflake database' — a pure read operation that retrieves metadata with no side effects.
Attacks that exploit this kind of access
List all schemas in a Snowflake database. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for snowflake_list_schemas: 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 Integrations MCP. Nothing to install.
snowflake_list_schemas 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 snowflake_list_schemas 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 snowflake_list_schemas. 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.
snowflake_list_schemas is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →