add_bounty · Manifold MCP: Risk & Policy

WHAT IT DOES

What add_bounty does on Manifold

AI agents use add_bounty to commit financial operations through Manifold — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why add_bounty needs a policy

Adding a bounty involves committing funds (Manifold Mana or real value) to a market as a reward. This is a financial commitment that cannot be trivially reversed, making it a Financial category action with high severity since an AI agent could repeatedly commit funds to markets without user intent.

From the tool's definition 'Add bounty to a market' — committing real or platform currency as a bounty reward

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_bounty Approval-gated

Any call to add_bounty is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_bounty": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Manifold, so you can run agents against it safely.

FAQ

Questions about add_bounty

What does the add_bounty tool do? +

Add bounty to 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.

How do I enforce a policy on add_bounty? +

Register the Manifold MCP server in PolicyLayer and add a rule for add_bounty: 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.

What risk level is add_bounty? +

add_bounty is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit add_bounty? +

Yes. Add a rate_limit block to the add_bounty 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.

How do I block add_bounty completely? +

Set action: deny in the PolicyLayer policy for add_bounty. 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.

What MCP server provides add_bounty? +

add_bounty 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.