# add

Add two integers.

Agent View of the PolicyLayer registry record for `add`. HTML page: https://policylayer.com/tools/agent-reliability-lab/add

## Facts

- Tool: `add`
- Server: Agent Reliability Lab (`Andrem19/agent-reliability-lab`) — https://policylayer.com/tools/agent-reliability-lab.md
- Homepage: https://github.com/Andrem19/agent-reliability-lab
- Risk category: Other (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "add",
    "arguments": {}
  }
}
```

## Why add is rated Low

Adding two integers is a stateless mathematical computation. It does not read from or write to any system, execute code, delete data, or involve finances. It is a utility/helper function that fits none of the primary risk categories.

From the tool's own definition: "'Add two integers' — this tool performs a pure arithmetic operation with no side effects, data access, execution, or financial implications."

## Use case

AI agents call add as a supporting operation in Agent Reliability Lab workflows.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agent Reliability Lab:

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

## Other tools on Agent Reliability Lab (2)

- `submit_demo` — Destructive — https://policylayer.com/tools/agent-reliability-lab/submit-demo.md
- `echo` — Write — https://policylayer.com/tools/agent-reliability-lab/echo.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agent-reliability-lab · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agent-reliability-lab