AI agents use strato.cdp.set-asset-supported to create or update resources in Griphook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Griphook environment.
Toggling asset support is a configuration change that can enable or disable an asset from being used as collateral in the lending/CDP system. This is a Write operation (reversible toggle), but carries high severity because disabling a supported asset could affect existing positions, liquidations, or user funds across the DeFi platform.
From the tool's definition 'Admin: toggle asset support' — enables or disables support for an asset in the CDP (Collateralized Debt Position) system
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Admin: toggle asset support. It is categorised as a Write tool in the Griphook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Griphook MCP server in PolicyLayer and add a rule for strato.cdp.set-asset-supported: 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 Griphook. Nothing to install.
strato.cdp.set-asset-supported 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 strato.cdp.set-asset-supported 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 strato.cdp.set-asset-supported. 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.
strato.cdp.set-asset-supported is provided by the Griphook MCP server (strato-net/strato-griphook). 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 →