AI agents use send_dm_to_group to create or update resources in Twikit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Twikit environment.
Sending direct messages to a group is a Write operation—it creates/delivers new data (messages) with reversible effects (messages can be deleted as shown by the 'delete_dm' sibling tool). It is not Destructive (messages are not permanently unrecoverable by design), not Execute (no arbitrary code/commands), not Financial (no money movement), and not Read (it modifies state).
From the tool's definition The tool name 'send_dm_to_group' indicates it sends direct messages to multiple users. Sibling tools on this server include 'delete_dm' and 'create_scheduled_tweet', establishing a pattern of social media write operations.
Documented attack patterns abuse exactly the kind of access send_dm_to_group gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Twikit, and nothing reaches the server without passing your rules. This is the rule we recommend for send_dm_to_group:
{
"version": "1",
"default": "deny",
"tools": {
"send_dm_to_group": {
"limits": [
{
"counter": "send_dm_to_group_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_dm_to_group 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_dm_to_group. It is categorised as a Write tool in the Twikit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Twikit MCP server in PolicyLayer and add a rule for send_dm_to_group: 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 Twikit. Nothing to install.
send_dm_to_group 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_to_group 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_to_group. 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_to_group is provided by the Twikit MCP server (tangivis/twitter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Twikit, 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.
59 Twikit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.