prompt_agent · MoluAbi MCP Server MCP: Risk & Policy

WHAT IT DOES

What prompt_agent does on MoluAbi MCP Server

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

WHY IT NEEDS A POLICY

Why prompt_agent needs a policy

The tool explicitly involves crypto payment, meaning it moves financial value (cryptocurrency) as part of its operation. This places it in the Financial category, which is the most severe. Misuse could result in unauthorized financial transactions via cryptocurrency, which are typically irreversible.

From the tool's definition Send a prompt to an agent with crypto payment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prompt_agent Approval-gated

Any call to prompt_agent 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": {
    "prompt_agent": {
      "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 MoluAbi MCP Server, so you can run agents against it safely.

FAQ

Questions about prompt_agent

What does the prompt_agent tool do? +

Send a prompt to an agent with crypto payment. It is categorised as a Financial tool in the MoluAbi MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on prompt_agent? +

Register the MoluAbi MCP Server MCP server in PolicyLayer and add a rule for prompt_agent: 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 MoluAbi MCP Server. Nothing to install.

What risk level is prompt_agent? +

prompt_agent 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 prompt_agent? +

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

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

prompt_agent is provided by the MoluAbi MCP Server MCP server (oregpt/moluabi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.