add_agent_tool · Smallest MCP: Risk & Policy

WHAT IT DOES

What add_agent_tool does on Smallest

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

WHY IT NEEDS A POLICY

Why add_agent_tool needs a policy

This tool modifies agent state by adding or updating API-call tools, which is a write operation. It doesn't delete or permanently destroy data (Destructive), execute arbitrary code directly (Execute), or move money (Financial).

From the tool's definition Tool description states "Add (or update) one or more API-call tools on a single_prompt agent", indicating it creates or modifies agent configurations by adding new capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_agent_tool Rate-limited

add_agent_tool 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_agent_tool": {
      "limits": [
        {
          "counter": "add_agent_tool_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 Smallest, so you can run agents against it safely.

FAQ

Questions about add_agent_tool

What does the add_agent_tool tool do? +

Add (or update) one or more API-call tools on a single_prompt agent. API-call tools let the agent make an HTTP request to an external API during a call — e.g. look up an order, book an appointment, or post to a CRM. It is categorised as a Write tool in the Smallest 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_agent_tool? +

Register the Smallest MCP server in PolicyLayer and add a rule for add_agent_tool: 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 Smallest. Nothing to install.

What risk level is add_agent_tool? +

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

Can I rate-limit add_agent_tool? +

Yes. Add a rate_limit block to the add_agent_tool 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_agent_tool completely? +

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

add_agent_tool is provided by the Smallest MCP server (@developer-smallestai/smallest-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.