CORTEX trading signals - direction, confidence, win rate for Solana tokens.
AI agents call get_trading_signals 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.
This tool queries and returns trading signal analysis data—direction recommendations, confidence scores, and win rate statistics. It performs no state mutations, does not execute trades, move funds, or trigger external operations. While the server architecture involves micropayments (x402 USDC), the tool itself is a Read operation that retrieves intelligence.
From the tool's definition Tool description states 'CORTEX trading signals - direction, confidence, win rate for Solana tokens.' It retrieves analytical signals and metrics without modifying any blockchain state, accounts, or positions.
Attacks that exploit this kind of access
CORTEX trading signals - direction, confidence, win rate for Solana tokens. 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 get_trading_signals: 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.
get_trading_signals 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 get_trading_signals 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 get_trading_signals. 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.
get_trading_signals 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 →