like_tweet · Agent Twitter Client MCP: Risk & Policy

WHAT IT DOES

What like_tweet does on Agent Twitter Client

AI agents use like_tweet to create or update resources in Agent Twitter Client — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Twitter Client environment.

WHY IT NEEDS A POLICY

Why like_tweet needs a policy

Liking a tweet is a reversible write operation that creates a social interaction on the platform. It does not delete data, execute code, or involve financial transactions. The blast radius is low since misuse would result in unwanted likes on tweets, which can be undone.

From the tool's definition 'Like a tweet' - this creates a like/reaction on a tweet, which is a reversible write action (can be unliked)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

like_tweet Rate-limited

like_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": {
    "like_tweet": {
      "limits": [
        {
          "counter": "like_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 Agent Twitter Client, so you can run agents against it safely.

FAQ

Questions about like_tweet

What does the like_tweet tool do? +

Like a tweet. It is categorised as a Write tool in the Agent Twitter Client MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on like_tweet? +

Register the Agent Twitter Client 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 Agent Twitter Client. Nothing to install.

What risk level is like_tweet? +

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

Can I rate-limit like_tweet? +

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.

How do I block like_tweet completely? +

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.

What MCP server provides like_tweet? +

like_tweet is provided by the Agent Twitter Client MCP server (theo-nash/twitter-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.