AI agents use place_bet to commit financial operations through Manifold — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Placing a bet on a prediction market constitutes a financial transaction, committing the user's funds (Mana or real money) to a market position. This is irreversible in the sense that the bet is placed and money is at risk. Financial is the highest severity category and clearly applies here. An AI agent misusing this tool could place large or unintended bets, causing significant financial loss.
From the tool's definition 'place_bet' and 'Place a bet on a market' — directly commits financial resources on a prediction market
Attacks that exploit this kind of access
Place a bet on a market. It is categorised as a Financial tool in the Manifold MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Manifold MCP server in PolicyLayer and add a rule for place_bet: 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 Manifold. Nothing to install.
place_bet 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 place_bet 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 place_bet. 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.
place_bet is provided by the Manifold MCP server (manifold-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
place_bet is one line of Manifold's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →