AI agents call dex_search to retrieve information from Coin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
DEX (decentralized exchange) search functionality on a market-data server would retrieve cryptocurrency exchange or trading information without modifying data. No evidence of execution, destruction, or financial transaction capabilities. Confidence is moderate (0.7) rather than high because the description is empty, creating some uncertainty about actual implementation details.
From the tool's definition Tool name 'dex_search' and server context indicate querying cryptocurrency market data. Server description states tools enable 'LLMs to answer market questions via natural language' and sibling tools are all data retrieval operations (get_*, compare_*,…
Attacks that exploit this kind of access
dex_search. It is categorised as a Read tool in the Coin MCP Server, which means it retrieves data without modifying state.
Register the Coin MCP server in PolicyLayer and add a rule for dex_search: 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 Coin. Nothing to install.
dex_search 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_search 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_search. 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_search is provided by the Coin MCP server (sweetcornna/coin-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 →