Skip to content

XCROP X (Twitter) data MCP server

io.xcrop/x-dataxcrop.iostreamable-httpv1.0.1Scanned

Read public X (Twitter) data and verify follows, reposts, replies and quotes. 14 read-only tools.

14 tools: 1 do something that can't be undone, 3 change things and 10 only read.

Tools: 0 delete, 1 irreversible, 3 write, 10 read.
  • Reads private data · 1
  • Reads text others write · 14
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the XCROP X (Twitter) data MCP server can do

The XCROP X (Twitter) data MCP server is published by xcrop.io, a domain the MCP Registry verified. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (get_tweet_replies) and create or change data (3 tools: get_tweet_quotes, check_follow and check_interaction), but cannot delete data. 10 tools only read.

1 tool reads private data (get_tweet_replies); 14 tools bring in text other people can write (get_user, get_user_tweets, search_tweets and 11 more).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 1.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

14 tools

Can't be undone 1Claude Code: ask
  • get_tweet_repliesReplies under an X post (its conversation).Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "get_tweet_replies" says "get": a word for reading.
    • The description's first verb is "reply": a word for sending, and what is sent cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • private-dataThe description's first sentence says "conversation": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_tweet_replies" says "get" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "reply" and "post": it reads posts, which other people can write.

    Findings

    • Warn

      The server marks "get_tweet_replies" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "get_tweet_replies" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Replies under an X post (its conversation). Costs 15 credits per reply returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Changes things 3Claude Code: ask
  • check_followDoes one X account follow another?Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Does one X account follow another? Returns both directions. Costs 50 credits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • check_interactionDid an account repost, reply to or quote a given X post?Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Did an account repost, reply to or quote a given X post? Built for giveaway, airdrop and quest verification. For reply and quote, min_tags requires that many @mentions in the text. Costs 50 credits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_tweet_quotesPosts that quote an X post.Reads text others write1 finding

    Why it is in this group

    • The name "get_tweet_quotes" says "get": a word for reading.
    • The description's first verb is "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_tweet_quotes" says "get" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post" and "post": it reads posts, which other people can write.

    Findings

    • Warn

      The server marks "get_tweet_quotes" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "get_tweet_quotes" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Posts that quote an X post. Costs 15 credits per quote returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 10Show 10 read-only tools
  • get_creditsCredits left on your XCROP key: plan allowance, used, remaining and top-up balance.Reads text others writeNo findings

    Why it is in this group

    • The name "get_credits" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Credits left on your XCROP key: plan allowance, used, remaining and top-up balance. Free.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_followersFollowers of an X account, newest first.Reads text others writeNo findings

    Why it is in this group

    • The name "get_followers" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Followers of an X account, newest first. Costs 1 credit per follower returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_followingAccounts an X account follows, newest first.Reads text others writeNo findings

    Why it is in this group

    • The name "get_following" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Accounts an X account follows, newest first. Costs 1 credit per account returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_tweetOne X post with its text, author, counts (likes, reposts, replies, quotes, views) and media.Reads text others writeNo findings

    Why it is in this group

    • The name "get_tweet" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_tweet" says "get" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    One X post with its text, author, counts (likes, reposts, replies, quotes, views) and media. Costs 15 credits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_tweet_retweetersAccounts that reposted (retweeted) an X post.Reads text others writeNo findings

    Why it is in this group

    • The name "get_tweet_retweeters" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_tweet_retweeters" says "get" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Accounts that reposted (retweeted) an X post. Costs 1 credit per account returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_userProfile of an X (Twitter) account: name, bio, followers, following, post count, verification, creation date.Reads text others writeNo findings

    Why it is in this group

    • The name "get_user" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Profile of an X (Twitter) account: name, bio, followers, following, post count, verification, creation date. Costs 18 credits.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_user_tweetsLatest posts of an X account (its Posts tab).Reads text others writeNo findings

    Why it is in this group

    • The name "get_user_tweets" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "get_user_tweets" says "get" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Latest posts of an X account (its Posts tab). Costs 15 credits per post returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • search_tweetsSearch X posts.Reads text others writeNo findings

    Why it is in this group

    • The name "search_tweets" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "search_tweets" says "search" and "tweet": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "search" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Search X posts. Supports X search operators in the query (from:, to:, lang:, min_faves:, since:, until:, -filter:replies). Costs 15 credits per post returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • search_usersFind X accounts by name or keyword.Reads text others writeNo findings

    Why it is in this group

    • The name "search_users" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find X accounts by name or keyword. Costs 18 credits per account returned.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write14
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:20 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://xcrop.io/api/mcp: tools/list returned 14 tools to an anonymous client, including get_tweet_replies (irreversible), get_tweet_quotes (write), check_follow (write), check_interaction (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "get_tweet_replies" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "get_tweet_replies" says "get": a word for reading.

    What this check looks for
  • The server marks "get_tweet_quotes" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "get_tweet_quotes" says "get": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http x-data https://xcrop.io/api/mcp --header 'X-API-Key: <your-x-api-key>'
claude mcp add --transport http x-data https://xcrop.io/api/mcp --header 'X-API-Key: <your-x-api-key>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__x-data__get_user",
      "mcp__x-data__get_user_tweets",
      "mcp__x-data__search_tweets",
      "mcp__x-data__search_users",
      "mcp__x-data__get_tweet",
      "mcp__x-data__get_tweet_retweeters",
      "mcp__x-data__get_followers",
      "mcp__x-data__get_following",
      "mcp__x-data__get_trending",
      "mcp__x-data__get_credits"
    ],
    "ask": [
      "mcp__x-data__get_tweet_replies",
      "mcp__x-data__get_tweet_quotes",
      "mcp__x-data__check_follow",
      "mcp__x-data__check_interaction"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as x-data. Review it before you use it.

Capability tags behind 14 rules
  • mcp__x-data__get_user untrusted-input
  • mcp__x-data__get_user_tweets untrusted-input
  • mcp__x-data__search_tweets untrusted-input
  • mcp__x-data__search_users untrusted-input
  • mcp__x-data__get_tweet untrusted-input
  • mcp__x-data__get_tweet_replies private-data, untrusted-input
  • mcp__x-data__get_tweet_quotes untrusted-input
  • mcp__x-data__get_tweet_retweeters untrusted-input
  • mcp__x-data__get_followers untrusted-input
  • mcp__x-data__get_following untrusted-input
  • mcp__x-data__check_follow untrusted-input
  • mcp__x-data__check_interaction untrusted-input
  • mcp__x-data__get_trending untrusted-input
  • mcp__x-data__get_credits untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.xcrop/x-data/verify?hash=79b5e8440972fd2dd0fbb8c2e3fb5d875d8ec34945538849b04ad5d784996147" | jq -e '.changed == false'

Pinned hash 79b5e8440972, from Nov 21, 2026, 08:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.xcrop/x-data/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.xcrop/x-data
[![Anlyon Radar](https://radar.anlyon.com/badge/io.xcrop/x-data.svg)](https://radar.anlyon.com/servers/io.xcrop/x-data)

Source: MCP Registry. Synced Nov 21, 2026, 08:18 UTC.

XCROP X (Twitter) data MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the XCROP X (Twitter) data MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the XCROP X (Twitter) data MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the XCROP X (Twitter) data MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: get_tweet_replies.

What tools does the XCROP X (Twitter) data MCP server have?

14 tools: 1 irreversible, 3 write, 10 read. get_tweet_replies, get_tweet_quotes, check_follow, check_interaction, get_user, get_user_tweets, search_tweets, search_users and 6 more.

Does the XCROP X (Twitter) data MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the XCROP X (Twitter) data MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the XCROP X (Twitter) data MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.