Modify warehouse settings for performance optimization
AI agents use alter_warehouse to create or update resources in Snowflake Developer MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Snowflake Developer MCP Server environment.
This tool modifies warehouse configuration settings, which is a reversible write operation. While warehouse modifications can impact performance and costs (affecting multiple users and operations), they do not delete data or trigger irreversible destructive actions.
From the tool's definition Tool name 'alter_warehouse' and description 'Modify warehouse settings for performance optimization' indicate modification of existing infrastructure configuration.
Attacks that exploit this kind of access
Modify warehouse settings for performance optimization. It is categorised as a Write tool in the Snowflake Developer MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Snowflake Developer MCP Server MCP server in PolicyLayer and add a rule for alter_warehouse: 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 Developer MCP Server. Nothing to install.
alter_warehouse is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the alter_warehouse 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 alter_warehouse. 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.
alter_warehouse is provided by the Snowflake Developer MCP Server MCP server (mcp-tg/snowflake-developer-kit). 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 →