AI agents use likePost to create or update resources in X Com MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your X Com MCP Server environment.
Liking a post is a reversible write operation that modifies the authenticated user's account state by creating a new like relationship. It does not delete, execute arbitrary code, or move money. While the blast radius is moderate (public engagement changes visible to other users), it remains a Write category action rather than more severe categories.
From the tool's definition Tool description states "Like a post on behalf of the authenticated user" — this creates a new like relationship/interaction, modifying the user's engagement state on X.com.
Documented attack patterns abuse exactly the kind of access likePost gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and X Com MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for likePost:
{
"version": "1",
"default": "deny",
"tools": {
"likePost": {
"limits": [
{
"counter": "likepost_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} likePost 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.
Like a post on behalf of the authenticated user. It is categorised as a Write tool in the X Com MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the X Com MCP Server MCP server in PolicyLayer and add a rule for likePost: 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 X Com MCP Server. Nothing to install.
likePost 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 likePost 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 likePost. 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.
likePost is provided by the X Com MCP Server MCP server (tiovikram/x.com-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from X Com MCP Server, 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.
21 X Com MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.