unlike-tweet · X MCP: Risk & Policy

WHAT IT DOES

What unlike-tweet does on X

AI agents use unlike-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.

WHY IT NEEDS A POLICY

Why unlike-tweet needs a policy

Unliking a tweet is a reversible modification to social engagement state (the user can re-like the tweet). It does not delete content, execute code, or involve finances. It writes a state change to the platform, making Write the appropriate category. Blast radius is low as it only affects a like counter on a single tweet.

From the tool's definition "Unlike a specific tweet" — removes a like/reaction from a tweet

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unlike-tweet Rate-limited

unlike-tweet 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "unlike-tweet": {
      "limits": [
        {
          "counter": "unlike-tweet_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches X, so you can run agents against it safely.

FAQ

Questions about unlike-tweet

What does the unlike-tweet tool do? +

Unlike 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.

How do I enforce a policy on unlike-tweet? +

Register the X MCP server in PolicyLayer and add a rule for unlike-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.

What risk level is unlike-tweet? +

unlike-tweet is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit unlike-tweet? +

Yes. Add a rate_limit block to the unlike-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.

How do I block unlike-tweet completely? +

Set action: deny in the PolicyLayer policy for unlike-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.

What MCP server provides unlike-tweet? +

unlike-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.

// THE FULL RECORD

unlike-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 →