add_answer · Manifold MCP: Risk & Policy

WHAT IT DOES

What add_answer does on Manifold

AI agents use add_answer to create or update resources in Manifold — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Manifold environment.

WHY IT NEEDS A POLICY

Why add_answer needs a policy

This tool creates new answer options within a market, modifying its state in a reversible manner. It is a Write operation rather than Execute because it performs a specific structured data modification (adding an answer choice) rather than arbitrary code execution.

From the tool's definition Tool description explicitly states 'Add a new answer to a multiple choice market' - a create/modify operation that adds new data to an existing market structure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_answer Rate-limited

add_answer stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_answer": {
      "limits": [
        {
          "counter": "add_answer_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT 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_answer

What does the add_answer tool do? +

Add a new answer to a multiple choice market. It is categorised as a Write tool in the Manifold MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_answer? +

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

add_answer is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_answer? +

Yes. Add a rate_limit block to the add_answer 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_answer completely? +

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

add_answer 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.