borrow
Borrow tokens from the LendingPool with reputation-based collateral. Auto-selects the USDC pool. Requires api_key.
This record as markdown: /tools/io-github-wirternow-agent-bank/borrow.md
What borrow does on Ai Agent Bank
AI agents use borrow to commit financial operations through Ai Agent Bank, usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | number | Yes | Amount to borrow |
api_key | string | Yes | Your api_key from register_agent |
urgency | number | — | Urgency level 1-10 (adds interest premium) |
agent_id | string | Yes | UUID of the borrowing agent |
collateral_token | string | Yes | Token symbol for collateral: WMATIC or WETH |
collateral_amount | number | Yes | Amount of collateral to deposit |
Parameters from the server's own tool schema.
Why borrow is rated Critical
This tool commits a financial obligation by borrowing tokens (USDC) from a lending pool on Polygon. Borrowing creates a debt liability that must be repaid, potentially with interest. Misuse by an AI agent could result in unauthorized loans, collateral at risk, and significant financial losses.
From the tool's definition 'Borrow tokens from the LendingPool with reputation-based collateral. Auto-selects the USDC pool.'
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
The rule that runs borrow safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ai Agent Bank, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For borrow, this is the rule to start with:
Any call to borrow is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Ai Agent Bank, apply this rule, and every borrow call is checked against it from then on.
Questions about borrow
Borrow tokens from the LendingPool with reputation-based collateral. Auto-selects the USDC pool. Requires api_key. It is categorised as a Financial tool in the Ai Agent Bank MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
borrow accepts 6 parameters: amount, api_key, urgency, agent_id, collateral_token, collateral_amount. Required: amount, api_key, agent_id, collateral_token, collateral_amount. The full parameter table on this page comes from the server's own tool schema.
Register the Ai Agent Bank MCP server in PolicyLayer and add a rule for borrow: 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 Ai Agent Bank. Nothing to install.
borrow 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 borrow 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 borrow. 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.
borrow is provided by the Ai Agent Bank MCP server (https://tdueqhfxyojmjgactdyc.supabase.co/functions/v1/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ai Agent Bank, and thousands of servers like it.
Across the catalogue