AI agents call strato.tokens to retrieve information from Griphook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data only (token information, balances, assets). It has no side effects, does not execute trades, transfers, or governance actions, and does not modify blockchain state. The blast radius of misuse is minimal—an attacker could learn account balances but cannot move funds or trigger irreversible actions. Despite being on a DeFi platform, this particular tool is purely informational.
From the tool's definition Tool description explicitly states 'Fetch token catalog, user balances, voucher balance, and earning assets' — all read operations with no modification, deletion, or execution of transactions.
Attacks that exploit this kind of access
Fetch token catalog, user balances, voucher balance, and earning assets. It is categorised as a Read tool in the Griphook MCP Server, which means it retrieves data without modifying state.
Register the Griphook MCP server in PolicyLayer and add a rule for strato.tokens: 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.tokens is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the strato.tokens 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.tokens. 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.tokens 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 →