Send a prompt to an AI model via SolanaProx. Costs are automatically deducted from your Solana wallet balance in USDC. Supports Claude and GPT-4 models. Use this for any AI inference task.
AI agents use ask_ai to commit financial operations through Solanaprox — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Every call to ask_ai results in an automatic deduction of USDC from the user's Solana wallet. This constitutes a direct financial obligation/payment, making it Financial category. Severity is critical because an AI agent could invoke this tool repeatedly at scale, draining the wallet with no per-call confirmation, and the transactions are irreversible on-chain.
From the tool's definition 'Costs are automatically deducted from your Solana wallet balance in USDC' — the tool triggers real financial transactions (USDC deduction from a Solana wallet) on every invocation.
Attacks that exploit this kind of access
Send a prompt to an AI model via SolanaProx. Costs are automatically deducted from your Solana wallet balance in USDC. Supports Claude and GPT-4 models. Use this for any AI inference task. It is categorised as a Financial tool in the Solanaprox MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Solanaprox MCP server in PolicyLayer and add a rule for ask_ai: 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 Solanaprox. Nothing to install.
ask_ai 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 ask_ai 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 ask_ai. 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.
ask_ai is provided by the Solanaprox MCP server (solanaprox/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 →