Full DrainBrain ML analysis. 5-model ensemble returns score 0-100, risk level, rug stage (0-5), honeypot detection, risk flags, temporal prediction.
AI agents call scan_token to retrieve information from Harvey Intel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the high-risk financial domain (Solana tokens, rug detection, honeypot analysis), the tool itself performs classification and retrieval only. It does not execute trades, modify token state, move funds, or trigger blockchain transactions.
From the tool's definition Tool name 'scan_token' with description stating it 'returns score 0-100, risk level, rug stage, honeypot detection, risk flags, temporal prediction' — all outputs are analytical assessments with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Full DrainBrain ML analysis. 5-model ensemble returns score 0-100, risk level, rug stage (0-5), honeypot detection, risk flags, temporal prediction. It is categorised as a Read tool in the Harvey Intel MCP Server, which means it retrieves data without modifying state.
Register the Harvey Intel MCP server in PolicyLayer and add a rule for scan_token: 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 Harvey Intel. Nothing to install.
scan_token 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_token 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_token. 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_token is provided by the Harvey Intel MCP server (meltingpixelsai/zero-core-intel). 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 →