propose_trade
AI agents use propose_trade to commit financial operations through Solana Trading MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool exists within a trading bot context where sibling tools perform token purchases and swaps. 'propose_trade' almost certainly initiates or stages a financial trade on the Solana blockchain. Even if it only 'proposes' rather than executes, it likely commits or stages a financial obligation.
From the tool's definition Tool name 'propose_trade' on a Solana trading server with sibling tools including 'buy_pumpfun_token', 'get_swap_quote', and 'get_risk_limits' strongly implies financial trading activity.
Attacks that exploit this kind of access
propose_trade. It is categorised as a Financial tool in the Solana Trading MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Solana Trading MCP Server MCP server in PolicyLayer and add a rule for propose_trade: 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 Solana Trading MCP Server. Nothing to install.
propose_trade is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the propose_trade 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 propose_trade. 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.
propose_trade is provided by the Solana Trading MCP Server MCP server (itskazgar/solana-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 →