// SCAN REPORT

Twikit

59 tools. 28 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

28 can modify or destroy data

31 read-only

59 tools total

Community server · catalogue entry verified 12/06/2026

How to control Twikit ↓

TOOL MAP

What Twikit exposes to your agents

Read (31) Write / Execute (23) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Twikit tools

Destructive · Low delete_bookmark Deleting a bookmark is an irreversible removal action. Destructive · High delete_dm Deleting a direct message is an irreversible operation that permanently removes data from the user's account. Destructive · Medium delete_retweet This tool removes a retweet action, which is an irreversible deletion of a previously made retweet. Destructive · High delete_scheduled_tweet Deleting a scheduled tweet is a destructive action that cannot be undone—the scheduled tweet is permanently removed from the user's queue.

28 of Twikit's 59 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Twikit

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

Deny destructive operations

{
  "delete_bookmark": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "remove_list_member": {
    "limits": [
      {
        "counter": "remove_list_member_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "download_tweet_video": {
    "limits": [
      {
        "counter": "download_tweet_video_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 Twikit — 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 TWIKIT →

Free to start. No card required.

FULL CATALOGUE

All 59 Twikit tools

DESTRUCTIVE 5 tools

Destructive delete_bookmark Remove a tweet from bookmarks. Destructive delete_dm Delete a direct message by ID. Destructive delete_retweet Un-retweet a tweet by ID. Destructive delete_scheduled_tweet delete_scheduled_tweet Destructive delete_tweet Delete a tweet by ID.

WRITE 23 tools

Write remove_list_member Remove a user from a Twitter List. Write block_user Block a user by screen name. Write follow_user Follow a user by screen name. Write join_community Join a Twitter Community. Write leave_community Leave a Twitter Community. Write like_tweet Like a tweet by ID. Write mute_user Mute a user by screen name. Write request_to_join_community request_to_join_community Write retweet Retweet a tweet by ID. Write unblock_user Unblock a user by screen name. Write unfavorite_tweet Unlike a tweet by ID. Write unfollow_user Unfollow a user by screen name. Write unmute_user Unmute a user by screen name. Write add_list_member Add a user to a Twitter List. Write bookmark_tweet Bookmark a tweet. Optionally add it to a bookmark folder. Write create_list Create a new Twitter List. Write create_poll create_poll Write create_scheduled_tweet create_scheduled_tweet Write edit_list edit_list Write send_dm send_dm Write send_dm_to_group send_dm_to_group Write send_tweet Send a tweet. Optionally reply to a tweet by ID. Write vote vote

READ 31 tools

EXPLORE

Related servers

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

FAQ

Questions about Twikit

Can an AI agent delete data through the Twikit MCP server? +

Yes. The Twikit server exposes 5 destructive tools including delete_bookmark, delete_dm, delete_retweet. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Twikit? +

The Twikit server has 23 write tools including remove_list_member, block_user, follow_user. 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 Twikit.

How many tools does the Twikit MCP server expose? +

59 tools across 3 categories: Destructive, Read, Write. 31 are read-only. 28 can modify, create, or delete data.

How do I enforce a policy on Twikit? +

Register the Twikit 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 Twikit tool call.

Deterministic rules across all 59 Twikit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TWIKIT →

Free to start. No card required.

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