Undo an action: unlike, unretweet, or delete tweet
AI agents call twitter_undo to permanently remove resources in Twitter Bridge MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool can delete tweets, which is irreversible destruction of user content. Unlike/unretweet are also undoable social actions but the presence of tweet deletion elevates this to Destructive. Misuse by an AI agent could result in permanent loss of posts, replies, or threads with no recovery path.
From the tool's definition 'delete tweet' — permanently removes a tweet; also 'unlike, unretweet' which are irreversible social actions
Documented attack patterns abuse exactly the kind of access twitter_undo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Twitter Bridge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for twitter_undo:
{
"version": "1",
"default": "deny",
"hide": [
"twitter_undo"
]
}twitter_undo disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Undo an action: unlike, unretweet, or delete tweet. It is categorised as a Destructive tool in the Twitter Bridge MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Twitter Bridge MCP server in PolicyLayer and add a rule for twitter_undo: 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 Bridge MCP. Nothing to install.
twitter_undo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the twitter_undo 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 twitter_undo. 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.
twitter_undo is provided by the Twitter Bridge MCP server (replica882/twitter-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Twitter Bridge MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Twitter Bridge MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.