AI agents use swap_token to commit financial operations through Baselings — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves funds by executing token swaps on a DEX (Uniswap V3), which constitutes a financial transaction involving real assets (USDC, ETH, or BTC on Base chain). Even with hard limits ($0.10/swap, $5/day), it commits financial obligations and moves money, placing it firmly in the Financial category.
From the tool's definition Execute a token swap on Uniswap V3 (Base)... $0.10 max per swap... $5/day... Uses dedicated trade wallet
Attacks that exploit this kind of access
Execute a token swap on Uniswap V3 (Base). Hard limits: $0.10 max per swap, 60s cooldown, $5/day. Uses dedicated trade wallet. All guardrails enforced automatically. 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 swap_token: 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.
swap_token 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 swap_token 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 swap_token. 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.
swap_token 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 →