search_pools
AI agents call search_pools to retrieve information from DEX Pools MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, this tool's name 'search_pools' and its placement among purely read-only sibling tools (get_pool_details, get_trending_pools, etc.) indicate it retrieves or queries DEX pool data without side effects. The server explicitly provides 'real-time access to DEX liquidity pool data' for analytics and intelligence.
From the tool's definition Tool name 'search_pools' combined with server context showing all sibling tools are read-only data retrieval functions (get_*, returning pool data, details, and analytics).
Attacks that exploit this kind of access
search_pools. It is categorised as a Read tool in the DEX Pools MCP MCP Server, which means it retrieves data without modifying state.
Register the DEX Pools MCP server in PolicyLayer and add a rule for search_pools: 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 DEX Pools MCP. Nothing to install.
search_pools 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 search_pools 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 search_pools. 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.
search_pools is provided by the DEX Pools MCP server (kukapay/dex-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 →