Deposit stablecoins to earn passive yield from borrowers
AI agents use granite_deposit to commit financial operations through Stacks AI MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Depositing stablecoins into a lending protocol is a financial transaction that moves money and creates financial obligations (yield commitments). Even though it is reversible (unlike destructive operations), it commits capital and generates financial exposure.
From the tool's definition Tool name 'granite_deposit' combined with description 'Deposit stablecoins to earn passive yield from borrowers' indicates movement of financial assets into a yield-bearing protocol. This commits user funds to a DeFi lending contract.
Attacks that exploit this kind of access
Deposit stablecoins to earn passive yield from borrowers. It is categorised as a Financial tool in the Stacks AI MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Stacks AI MCP Server MCP server in PolicyLayer and add a rule for granite_deposit: 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 Stacks AI MCP Server. Nothing to install.
granite_deposit is a Financial 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 granite_deposit 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 granite_deposit. 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.
granite_deposit is provided by the Stacks AI MCP Server MCP server (stack-ai-mcp/stacks-mcp-server). 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 →