send_mana · Manifold MCP: Risk & Policy

WHAT IT DOES

What send_mana does on Manifold

AI agents use send_mana 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 send_mana needs a policy

Sending mana is a financial action: it moves platform currency from one account to another. This is irreversible without the recipient's cooperation, and an AI agent misusing this tool could drain a user's mana balance. Financial is the most severe applicable category.

From the tool's definition 'send_mana' and 'Send mana to other users' — this tool transfers the platform's currency (mana) to other users, constituting a financial transfer operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_mana Approval-gated

Any call to send_mana 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": {
    "send_mana": {
      "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 send_mana

What does the send_mana tool do? +

Send mana to other users. 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 send_mana? +

Register the Manifold MCP server in PolicyLayer and add a rule for send_mana: 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 send_mana? +

send_mana 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 send_mana? +

Yes. Add a rate_limit block to the send_mana 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 send_mana completely? +

Set action: deny in the PolicyLayer policy for send_mana. 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 send_mana? +

send_mana 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.