get_token_pools_v3
AI agents call get_token_pools_v3 to retrieve information from Uniswap Pools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve structured data about Uniswap pools without modifying state. The 'get' prefix and context of 'querying' suggest a read operation. Although the tool description is empty, the naming convention and server context provide reasonable evidence.
From the tool's definition The tool name is 'get_token_pools_v3' with a 'get' prefix (verb pattern for retrieval operations); the server description states 'querying Uniswap pools/pairs...delivering clean, structured results'; sibling tools are similarly named 'get_pool_data',…
Attacks that exploit this kind of access
get_token_pools_v3. It is categorised as a Read tool in the Uniswap Pools MCP Server, which means it retrieves data without modifying state.
Register the Uniswap Pools MCP server in PolicyLayer and add a rule for get_token_pools_v3: 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 Uniswap Pools. Nothing to install.
get_token_pools_v3 is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_token_pools_v3 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 get_token_pools_v3. 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.
get_token_pools_v3 is provided by the Uniswap Pools MCP server (kukapay/uniswap-pools-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 →