add · Remote MCP Server (Authless) MCP: Risk & Policy

WHAT IT DOES

What add does on Remote MCP Server (Authless)

AI agents call add as a supporting operation in Remote MCP Server (Authless) workflows.

WHY IT NEEDS A POLICY

Why add needs a policy

The description is empty, so classification relies on the tool name alone. Given the sibling tool 'calculate', 'add' most likely performs arithmetic addition, which is a read/compute operation with no side effects. However, without a description, confidence is low. Defaulting to Other given the ambiguity, though Read would also be reasonable.

From the tool's definition Tool name is 'add' with an empty description. Sibling tools include 'calculate' and 'whoami', suggesting this is likely a simple arithmetic addition tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add Rate-limited

add gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add": {
      "limits": [
        {
          "counter": "add_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about add

What does the add tool do? +

add. It is categorised as a Other tool in the Remote MCP Server (Authless) MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on add? +

Register the Remote MCP Server (Authless) MCP server in PolicyLayer and add a rule for add: 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 Remote MCP Server (Authless). Nothing to install.

What risk level is add? +

add is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit add? +

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

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

add is provided by the Remote MCP Server (Authless) MCP server (itoyuya1005/remote-mcp-server-authless). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.