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