This record as markdown: /tools/libi/libi.save-model-schema-cache.md
What libi.save_model_schema_cache does on Libi
AI agents use libi.save_model_schema_cache to create or update resources in Libi, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Libi environment.
Why libi.save_model_schema_cache is rated Medium
Saves cached data reversibly, a write operation without side effects or destructive impact.
From the tool's definition Cache an endpoint
Attacks that exploit this kind of access
The rule that runs libi.save_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.save_model_schema_cache, this is the rule to start with:
libi.save_model_schema_cache stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Libi, apply this rule, and every libi.save_model_schema_cache call is checked against it from then on.
Questions about libi.save_model_schema_cache
Cache an endpoint. It is categorised as a Write tool in the Libi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Libi MCP server in PolicyLayer and add a rule for libi.save_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.save_model_schema_cache 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 libi.save_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.save_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.save_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.
This server
Across the catalogue