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.
This record as markdown: /tools/io-github-razz-games-razz/razz-send-dm.md
What razz_send_dm does on Razz Games
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
content | string | Yes | Message content |
toUserId | string | Yes | Recipient's account ID |
replyToId | string | — | DM ID to reply to |
Parameters from the server's own tool schema.
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 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 signalsAccepts raw HTML/template content (content)
Attacks that exploit this kind of access
The rule that runs razz_send_dm safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Razz Games, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For razz_send_dm, this is the rule to start with:
razz_send_dm 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Razz Games, apply this rule, and every razz_send_dm call is checked against it from then on.
Questions about 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. It is categorised as a Write tool in the Razz Games MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
razz_send_dm accepts 3 parameters: content, toUserId, replyToId. Required: content, toUserId. The full parameter table on this page comes from the server's own tool schema.
Register the Razz Games MCP server in PolicyLayer and add a rule for razz_send_dm: 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 Razz Games. Nothing to install.
razz_send_dm is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the razz_send_dm 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.
Set action: deny in the PolicyLayer policy for razz_send_dm. 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.
razz_send_dm is provided by the Razz Games MCP server (@razzgames/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Razz Games, and thousands of servers like it.
This server
Across the catalogue