Create new DragonSwap V3 pool for token pair and fee tier
AI agents use create_pool to create or update resources in SEI MCP Server V2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SEI MCP Server V2 environment.
Creating a liquidity pool is a Write operation: it creates new, persistent on-chain data structures (the pool contract and its state) that are intended to be permanent. It is not merely querying data (Read), and while it writes rather than deletes, it's not Destructive.
From the tool's definition Tool name 'create_pool' and description state it 'Create new DragonSwap V3 pool for token pair and fee tier' — a blockchain operation that irreversibly writes new state (a liquidity pool) to the Sei blockchain.
Attacks that exploit this kind of access
Create new DragonSwap V3 pool for token pair and fee tier. It is categorised as a Write tool in the SEI MCP Server V2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SEI MCP Server V2 MCP server in PolicyLayer and add a rule for create_pool: 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.
create_pool is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_pool 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 create_pool. 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.
create_pool 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 →