Execute a token swap on DragonSwap
AI agents invoke execute_swap to trigger actions in SEI MCP Server V2. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While this involves financial assets, it is primarily an execution of a smart contract interaction (swap) rather than a direct payment or money transfer in the traditional sense. However, it does move tokens between parties, making it high severity. The most precise category is Execute since it runs an external blockchain operation whose effects depend on arguments (token pair, amount, slippage).
From the tool's definition "Execute a token swap on DragonSwap" — performs an on-chain token swap, triggering an external financial operation on a DEX
Attacks that exploit this kind of access
Execute a token swap on DragonSwap. It is categorised as a Execute tool in the SEI MCP Server V2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SEI MCP Server V2 MCP server in PolicyLayer and add a rule for execute_swap: 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 SEI MCP Server V2. Nothing to install.
execute_swap is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_swap 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 execute_swap. 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.
execute_swap is provided by the SEI MCP Server V2 MCP server (testinguser1111111/sei-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 →