clear_cache
AI agents invoke clear_cache to trigger actions in Fabric Dw Mcp Cli. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Clearing a cache on a data warehouse system is an operational action that triggers an external operation (invalidating cached query results or metadata), which is non-trivial and could impact performance or data consistency. It is not purely a read, and while it may be reversible (cache repopulates), the act of clearing is an execution-type operation. The empty description lowers confidence significantly.
From the tool's definition Tool name 'clear_cache' on a server for administering Microsoft Fabric Data Warehouses; description is empty.
Attacks that exploit this kind of access
clear_cache. It is categorised as a Execute tool in the Fabric Dw Mcp Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fabric Dw Mcp Cli MCP server in PolicyLayer and add a rule for clear_cache: 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 Fabric Dw Mcp Cli. Nothing to install.
clear_cache is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the clear_cache 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 clear_cache. 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.
clear_cache is provided by the Fabric Dw Mcp Cli MCP server (sdebruyn/fabric-dw-mcp-cli). 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 →