Send a tweet. Optionally reply to a tweet by ID.
AI agents use send_tweet 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.
This tool creates new, reversible content on a social media platform. While tweets can be deleted, the primary action is creation/publication, making this a Write operation rather than Execute (which would be for running arbitrary code) or Destructive (which would be for irreversible deletion).
From the tool's definition Tool name 'send_tweet' and description 'Send a tweet' indicate creation of new content on Twitter/X platform. The optional reply-to functionality extends this to creating threaded content.
Documented attack patterns abuse exactly the kind of access send_tweet 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_tweet:
{
"version": "1",
"default": "deny",
"tools": {
"send_tweet": {
"limits": [
{
"counter": "send_tweet_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_tweet 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 tweet. Optionally reply to a tweet by ID. 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_tweet: 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_tweet 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_tweet 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_tweet. 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_tweet 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.