libi.invalidate_model_schema_cache
Drop a cached endpoint schema. Call this when a generation fails because the cached schema was wrong, then re-fetch.
This record as markdown: /tools/libi/libi.invalidate-model-schema-cache.md
What libi.invalidate_model_schema_cache does on Libi
AI agents call libi.invalidate_model_schema_cache to permanently remove resources in Libi, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why libi.invalidate_model_schema_cache is rated Critical
Irreversibly removes cached schema data, though impact is limited to cache only.
From the tool's definition Drop a cached endpoint schema
Attacks that exploit this kind of access
The rule that runs libi.invalidate_model_schema_cache safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Libi, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For libi.invalidate_model_schema_cache, this is the rule to start with:
libi.invalidate_model_schema_cache is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Libi, apply this rule, and every libi.invalidate_model_schema_cache call is checked against it from then on.
Questions about libi.invalidate_model_schema_cache
Drop a cached endpoint schema. Call this when a generation fails because the cached schema was wrong, then re-fetch. It is categorised as a Destructive tool in the Libi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Libi MCP server in PolicyLayer and add a rule for libi.invalidate_model_schema_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 Libi. Nothing to install.
libi.invalidate_model_schema_cache is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the libi.invalidate_model_schema_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 libi.invalidate_model_schema_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.
libi.invalidate_model_schema_cache is provided by the Libi MCP server (Nagellabs/libi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Libi, and thousands of servers like it.
Across the catalogue