// SCAN REPORT

X

20 tools. 9 can modify or destroy data without limits.

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

Last updated: 7 Jul 2026

9 can modify or destroy data

11 read-only

20 tools total

Community server · catalogue entry checked 07/07/2026

How to control X ↓

TOOL MAP

What X exposes to your agents

Read (11) Write / Execute (9) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous X tools

Write · Medium unretweet This tool modifies social media state by removing a retweet, which is a reversible write operation (the user can retweet again). Write · Low add-delete-bookmark Bookmarking is a reversible user preference action that modifies data (bookmark list) but does not delete underlying content, execute external operations, or affect financial systems. Write · Medium advanced-tweet This tool creates new data (tweets) on a social media platform, which is a reversible write operation. Write · Medium post-tweet This tool creates new data (a tweet) on a social media platform, which is reversible (tweets can be deleted).

9 of X's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control X

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

Rate limit write operations

{
  "add-delete-bookmark": {
    "limits": [
      {
        "counter": "add-delete-bookmark_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get-community": {
    "limits": [
      {
        "counter": "get-community_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 X — 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 X →

Instant setup, no code required.

FULL CATALOGUE

All 20 X tools

WRITE 9 tools

Write add-delete-bookmark Add or delete a bookmark for a specific tweet Write advanced-tweet Post a tweet with advanced options like reply to a tweet, quote a specific tweet, or create a poll for the twe Write like-tweet Like a specific tweet Write post-tweet Post a tweet with the specified content Write quote-a-tweet Quote a specific tweet Write retweet Retweet a specific tweet Write tweet-thread Post a thread of tweets Write unlike-tweet Unlike a specific tweet Write unretweet Remove a retweet from a specific tweet

READ 11 tools

Read get-community Get details for a specific X community Read get-home-timeline Get tweets from your home timeline Read get-my-details Get my X account details Read get-quoted-tweets Get tweets that quote a specific tweet Read get-tweets Get one or more tweets by their IDs Read get-user-by-username Get details for a specific X user by username Read get-user-details Get details for a specific X user by ID Read get-user-followers Get followers of a specific X user Read get-user-following Get accounts that a specific X user is following Read get-user-timeline Get tweets from a specific user Read search-communities Search for X communities by keyword

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about X

How do I prevent bulk modifications through X? +

The X server has 9 write tools including add-delete-bookmark, advanced-tweet, like-tweet. 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 X.

How many tools does the X MCP server expose? +

20 tools across 3 categories: Destructive, Read, Write. 11 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on X? +

Register the X 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 X tool call.

Deterministic rules across all 20 X tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON X →

Instant setup, no code required.

20 X tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from X's registry record.

The record behind this page: 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 →