AI agents use deposit_garden to commit financial operations through Baselings — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Depositing tokens into yield-generating pools is a financial transaction that commits user assets and creates financial obligations/positions. Even though the yield may be claimed separately, the deposit itself locks capital and creates financial exposure. This qualifies as Financial rather than Write because it involves yield generation and potential loss of assets.
From the tool's definition The tool enables deposit of POOP tokens into a garden pool 'for yield', which generates financial returns (USDC, ETH, or BTC as stated in server description). This commits a financial asset to earn yields.
Attacks that exploit this kind of access
Deposit POOP into a garden pool for yield. It is categorised as a Financial tool in the Baselings MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Baselings MCP server in PolicyLayer and add a rule for deposit_garden: 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 Baselings. Nothing to install.
deposit_garden 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 deposit_garden 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 deposit_garden. 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.
deposit_garden is provided by the Baselings MCP server (jimbo530/baselings-mcp). 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 →