AI agents call scan_exchange_divergence to retrieve information from Asterdex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data analysis and market intelligence tool. It compares market metrics across exchanges to identify trading opportunities, but performs no write, execute, destructive, or financial actions itself. The worst-case misuse is that an agent could receive biased market analysis, but the tool itself cannot modify positions, execute trades, or cause financial harm.
From the tool's definition The tool 'scan_exchange_divergence' scans for pairs and finds opportunities based on market data comparison (volume, OI, funding). It retrieves and analyzes data without modifying positions, executing orders, or moving funds.
Attacks that exploit this kind of access
Scan for pairs where Binance and Aster show significant divergence in volume, OI, or funding. Finds opportunities where one exchange is leading. It is categorised as a Read tool in the Asterdex MCP Server, which means it retrieves data without modifying state.
Register the Asterdex MCP server in PolicyLayer and add a rule for scan_exchange_divergence: 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 Asterdex. Nothing to install.
scan_exchange_divergence 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 scan_exchange_divergence 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 scan_exchange_divergence. 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.
scan_exchange_divergence is provided by the Asterdex MCP server (tyranosurasmax/asterdex-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 →