AI agents use like-tweet to create or update resources in X — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your X environment.
Liking a tweet is a write operation (creates a 'like' record on the platform). It is reversible (can be unliked) and has minimal blast radius — at worst it signals approval of content on behalf of the user.
From the tool's definition 'Like a specific tweet' — creates a like/reaction on a tweet, which is a reversible social action
Attacks that exploit this kind of access
Like a specific tweet. It is categorised as a Write tool in the X MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the X MCP server in PolicyLayer and add a rule for like-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 X. Nothing to install.
like-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 like-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 like-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.
like-tweet is provided by the X MCP server (siddheshutd/x-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
like-tweet is one line of X's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →