Follow or unfollow a Twitter user
AI agents use follow_user 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.
Following or unfollowing a user modifies the account's social graph/relationship state on Twitter. This is a reversible write action (you can unfollow/re-follow), not destructive. Misuse could lead to unwanted follows or unfollows at scale, affecting account reputation or triggering spam/bot detection.
From the tool's definition Follow or unfollow a Twitter user
Documented attack patterns abuse exactly the kind of access follow_user 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 follow_user:
{
"version": "1",
"default": "deny",
"tools": {
"follow_user": {
"limits": [
{
"counter": "follow_user_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}follow_user 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.
Follow or unfollow a Twitter user. 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 follow_user: 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.
follow_user 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 follow_user 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 follow_user. 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.
follow_user 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.