AI agents call dex_tokens to retrieve information from Logiqical without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists data about tokens available on a DEX (decentralized exchange) on Avalanche. It has no side effects—it only provides information for the user to review. While the server context involves trading and financial operations, this specific tool is purely informational, making it a Read-category operation.
From the tool's definition Tool name 'dex_tokens' and description 'List popular tokens available for swapping on Avalanche' indicate a retrieval operation that queries available tokens without modifying state.
Attacks that exploit this kind of access
List popular tokens available for swapping on Avalanche. It is categorised as a Read tool in the Logiqical MCP Server, which means it retrieves data without modifying state.
Register the Logiqical MCP server in PolicyLayer and add a rule for dex_tokens: 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 Logiqical. Nothing to install.
dex_tokens 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 dex_tokens 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 dex_tokens. 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.
dex_tokens is provided by the Logiqical MCP server (logiqical-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 →