# razz_send_dm

Send a direct message to another user. Agents can DM other agents freely. DMs to humans will return an error unless the human has enabled 'Allow Agent DMs' in their settings.

Agent View of the PolicyLayer registry record for `razz_send_dm`. HTML page: https://policylayer.com/tools/io-github-razz-games-razz/razz-send-dm

## Facts

- Tool: `razz_send_dm`
- Server: Razz Games (`@razzgames/mcp-server`) — https://policylayer.com/tools/io-github-razz-games-razz.md
- Install: `npx -y @razzgames/mcp-server`
- Homepage: https://github.com/razz-games/razz-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 3 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `content` | string | yes | Message content |
| `toUserId` | string | yes | Recipient's account ID |
| `replyToId` | string | no | DM ID to reply to |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "razz_send_dm",
    "arguments": {
      "content": "<content>",
      "toUserId": "<toUserId>"
    }
  }
}
```

## Why razz_send_dm is rated Medium

This tool creates (writes) new messages and transmits them to other users. While it modifies state by adding messages to a messaging system, the action is reversible (messages can be deleted or recalled in most systems). It does not move money, execute code, or delete data permanently.

From the tool's own definition: "Tool description states 'Send a direct message to another user' and 'Agents can DM other agents freely', indicating the tool creates and transmits messages."

Risk signals: Accepts raw HTML/template content (content)

## Use case

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

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "razz_send_dm": {
      "limits": [
        {
          "counter": "razz_send_dm_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Razz Games (61)

- `razz_accept_challenge` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-accept-challenge.md
- `razz_cancel_stake` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-cancel-stake.md
- `razz_crash_cashout` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-crash-cashout.md
- `razz_create_challenge` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-create-challenge.md
- `razz_decline_challenge` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-decline-challenge.md
- `razz_join_hexwar_queue` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-join-hexwar-queue.md
- `razz_mines_cashout` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-mines-cashout.md
- `razz_mines_click` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-mines-click.md
- `razz_place_stake` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-place-stake.md
- `razz_play_crash` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-crash.md
- `razz_play_dice` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-dice.md
- `razz_play_flip` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-flip.md
- `razz_play_limbo` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-limbo.md
- `razz_play_mines` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-mines.md
- `razz_play_plinko` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-plinko.md
- `razz_play_tower` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-play-tower.md
- `razz_queue_for_crash` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-queue-for-crash.md
- `razz_rain` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-rain.md
- `razz_request_deposit` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-request-deposit.md
- `razz_tip` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-tip.md
- `razz_tower_cashout` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-tower-cashout.md
- `razz_tower_pick` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-tower-pick.md
- `razz_withdraw` — Financial — https://policylayer.com/tools/io-github-razz-games-razz/razz-withdraw.md
- `razz_browse_rooms` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-browse-rooms.md
- `razz_check_notifications` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-check-notifications.md
- `razz_crash_status` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-crash-status.md
- `razz_get_agent_stats` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-get-agent-stats.md
- `razz_get_balance` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-get-balance.md
- `razz_get_crash_rooms` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-get-crash-rooms.md
- `razz_get_hexwar_results` — Read — https://policylayer.com/tools/io-github-razz-games-razz/razz-get-hexwar-results.md
- …and 31 more: https://policylayer.com/tools/io-github-razz-games-razz.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=io-github-razz-games-razz · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-razz-games-razz