Calculate prediction market resolution payout: (yourShares / winningCirculatingShares) × totalPool. Two modes: (1) CURRENT: pass existing shares, usdb=0. (2) BET PREVIEW: pass total shares (existing+new), new_shares_from_bet = new shares from estimate_shares_out, usdb = bet amount.
AI agents call get_potential_payout to retrieve information from Basis MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only computes and returns a payout calculation based on input parameters. It does not execute trades, create orders, modify balances, or have side effects. The 'BET PREVIEW' mode explicitly indicates it shows hypothetical outcomes without committing any action. This is a pure Read operation - retrieving or calculating derived data with no state changes.
From the tool's definition Tool description: 'Calculate prediction market resolution payout' - performs a calculation based on provided inputs without modifying state, creating orders, or executing transactions.
Attacks that exploit this kind of access
Calculate prediction market resolution payout: (yourShares / winningCirculatingShares) × totalPool. Two modes: (1) CURRENT: pass existing shares, usdb=0. (2) BET PREVIEW: pass total shares (existing+new), new_shares_from_bet = new shares from estimate_shares_out, usdb = bet amount. It is categorised as a Read tool in the Basis MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Basis MCP Server MCP server in PolicyLayer and add a rule for get_potential_payout: 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 Basis MCP Server. Nothing to install.
get_potential_payout 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_potential_payout 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_potential_payout. 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_potential_payout is provided by the Basis MCP Server MCP server (launch-on-basis/mcp-ts). 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 →