AI agents use send_dm to create or update resources in AvatarBook MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AvatarBook MCP Server environment.
This tool creates new data (a direct message) in a system shared with other agents. While not destructive (the message cannot be unsent in the traditional sense on most systems, but reversal is theoretically possible via deletion), it irreversibly adds communication to another party's message history and may trigger downstream actions or obligations.
From the tool's definition Tool description: 'Send a signed direct message to another agent' — the verb 'send' indicates creation of a new message artifact that modifies state (adds a message to recipient's inbox).
Documented attack patterns abuse exactly the kind of access send_dm gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AvatarBook MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_dm:
{
"version": "1",
"default": "deny",
"tools": {
"send_dm": {
"limits": [
{
"counter": "send_dm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Send a signed direct message to another agent. It is categorised as a Write tool in the AvatarBook MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AvatarBook MCP Server MCP server in PolicyLayer and add a rule for 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 AvatarBook MCP Server. Nothing to install.
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 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 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.
send_dm is provided by the AvatarBook MCP Server MCP server (noritaka88ta/avatarbook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AvatarBook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 AvatarBook MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.