// SCAN REPORT

Twitter

13 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

6 can modify or destroy data

7 read-only

13 tools total

Community server · catalogue entry verified 12/06/2026

How to control Twitter ↓

TOOL MAP

What Twitter exposes to your agents

Read (7) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Twitter tools

Write · Medium create_note This tool creates new data (a note) without permanently destroying anything. Write · Medium create_thread This tool creates new social media posts/content, which is a Write operation (reversible modification of data). Write · Medium post_tweet Posting a tweet creates new social media content that is reversible (can be deleted later). Write · Medium follow_user Following or unfollowing a user modifies the account's social graph/relationship state on Twitter.

6 of Twitter's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Twitter

PolicyLayer is an MCP gateway — it sits between your AI agents and Twitter, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "follow_user": {
    "limits": [
      {
        "counter": "follow_user_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_list_tweets": {
    "limits": [
      {
        "counter": "get_list_tweets_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Twitter — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TWITTER →

Free to start. No card required.

FULL CATALOGUE

All 13 Twitter tools

WRITE 6 tools

Write follow_user Follow or unfollow a Twitter user Write like_tweet Like or unlike a tweet Write retweet Retweet or undo retweet of a tweet Write create_note Create a new note Write create_thread Create a Twitter thread (a series of connected tweets) Write post_tweet Post a new tweet, optionally with media or as a quote tweet

READ 7 tools

Read get_list_tweets Get tweets from a Twitter list Read get_profile Get a Twitter user Read get_timeline Get tweets from a user Read get_trends Get current trending topics on Twitter Read get_tweets Get recent tweets from a user Read get_user_relationships Get a user Read search_tweets Search for tweets by hashtag or keyword

FAQ

Questions about Twitter

How do I prevent bulk modifications through Twitter? +

The Twitter server has 6 write tools including follow_user, like_tweet, retweet. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Twitter.

How many tools does the Twitter MCP server expose? +

13 tools across 2 categories: Read, Write. 7 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Twitter? +

Register the Twitter MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Twitter tool call.

Deterministic rules across all 13 Twitter tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TWITTER →

Free to start. No card required.

13 Twitter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.