Post a new tweet, optionally with media or as a quote tweet
AI agents use post_tweet to create or update resources in Twitter — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Twitter environment.
Posting a tweet creates new social media content that is reversible (can be deleted later). It does not execute arbitrary code, delete data permanently, or move money. The 'medium' severity reflects that an AI agent could spam, impersonate, or post misleading content at scale, but the blast radius is limited by Twitter's rate limits and the content remains removable.
From the tool's definition Tool description states 'Post a new tweet' which creates new content on Twitter. This is a write operation that creates data reversibly (tweets can be deleted).
Documented attack patterns abuse exactly the kind of access post_tweet gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Twitter, and nothing reaches the server without passing your rules. This is the rule we recommend for post_tweet:
{
"version": "1",
"default": "deny",
"tools": {
"post_tweet": {
"limits": [
{
"counter": "post_tweet_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}post_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.
Post a new tweet, optionally with media or as a quote tweet. It is categorised as a Write tool in the Twitter MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Twitter MCP server in PolicyLayer and add a rule for post_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 Twitter. Nothing to install.
post_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 post_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 post_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.
post_tweet is provided by the Twitter MCP server (twitter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Twitter, 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.
13 Twitter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.