Skip to content

Twitter / X data for agents MCP server

sh.fetcher.twitter/mcptwitter.fetcher.shstreamable-httpv1.0.0Scanned

15 Twitter / X endpoints. Pay per call in USDC via x402.

17 tools: 3 do something that can't be undone, 10 change things and 4 only read.

Tools: 0 delete, 3 irreversible, 10 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

13 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.

What the Twitter / X data for agents MCP server can do

The Twitter / X data for agents MCP server is published by twitter.fetcher.sh, a domain the MCP Registry verified. It has 17 tools. It can do things that cannot be undone, such as sending, paying or publishing (twitter_tweet_replies, twitter_user_replies and topup_credits) and create or change data (10 tools: twitter_handle, twitter_handle_about, twitter_trends, twitter_tweet and 6 more), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (twitter_list_tweets); 2 tools can send data out of your system (twitter_tweet_replies and twitter_user_replies).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 1.0.0.

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.

17 tools

Can't be undone 3Claude Code: ask
  • topup_creditsPaid (the amount you choose, minimum $1).No findings

    Why it is in this group

    • The name "topup_credits" says "topup": a word that usually means money moves, which cannot be taken back.
    • The description says "cannot be recovered".
    Description, as the server wrote it
    Paid (the amount you choose, minimum $1). Buy prepaid credits with x402 so later calls skip the per-call payment round trip. With an Authorization: Bearer bby_live_... header on this connection it recharges that key. Without one, the paying wallet becomes the account and a new API key is minted and returned once — store it as a secret, it cannot be recovered.
  • twitter_tweet_repliesPaid ($0.005).Can send data outNo findings

    Why it is in this group

    • The name "twitter_tweet_replies" says "reply": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "twitter_tweet_replies" says "reply": it sends or publishes something to other people.
    Description, as the server wrote it
    Paid ($0.005). Tweet replies — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_user_repliesPaid ($0.005).Can send data outNo findings

    Why it is in this group

    • The name "twitter_user_replies" says "reply": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "twitter_user_replies" says "reply": it sends or publishes something to other people.
    Description, as the server wrote it
    Paid ($0.005). User replies — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
Changes things 10Claude Code: ask
  • check_balanceFree.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Free. Show the remaining credit balance for the API key sent in this connection's Authorization header. Call this before a long run of paid requests.
  • twitter_handlePaid ($0.005).No findings

    Why it is in this group

    • The name "twitter_handle" says "handle": a word for a change.
    Description, as the server wrote it
    Paid ($0.005). Handle — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_handle_aboutPaid ($0.005).No findings

    Why it is in this group

    • The name "twitter_handle_about" says "handle": a word for a change.
    Description, as the server wrote it
    Paid ($0.005). Handle about — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_tweetPaid ($0.002).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.002). Tweet — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_tweet_retweetersPaid ($0.005).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.005). Tweet retweeters — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_userPaid ($0.005).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.005). User — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_user_followersPaid ($0.005).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.005). User followers — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_user_followingsPaid ($0.005).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.005). User followings — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_user_tweetsPaid ($0.005).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Paid ($0.005). User tweets — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
Only reads 4Show 4 read-only tools
  • twitter_list_membersPaid ($0.005).No findings

    Why it is in this group

    • The name "twitter_list_members" says "list": a word for reading.
    Description, as the server wrote it
    Paid ($0.005). List members — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_list_tweetsPaid ($0.005).Reads text others writeNo findings

    Why it is in this group

    • The name "twitter_list_tweets" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "twitter_list_tweets" says "list" and "tweet": it reads posts, which other people can write.
    Description, as the server wrote it
    Paid ($0.005). List tweets — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.
  • twitter_search_usersPaid ($0.005).No findings

    Why it is in this group

    • The name "twitter_search_users" says "search": a word for reading.
    Description, as the server wrote it
    Paid ($0.005). Search users — Twitter / X. Live data as JSON. Pay with x402 or an Authorization: Bearer bby_live_... credits key.

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 private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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 20, 2026, 19:26 UTC, unchanged since Oct 22, 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
13
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://twitter.fetcher.sh/.well-known/oauth-protected-resource
Authorization servers
https://twitter.fetcher.sh
Legacy HTTP+SSE transport
no
Dynamic client registration
no
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 13 tools that change things (3 irreversible, 10 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://twitter.fetcher.sh/mcp: tools/list returned 17 tools to an anonymous client, including twitter_tweet_replies (irreversible), twitter_user_replies (irreversible), topup_credits (irreversible), twitter_handle (write), twitter_handle_about (write) and 8 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http twitter https://twitter.fetcher.sh/mcp
claude mcp add --transport http twitter https://twitter.fetcher.sh/mcp

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__twitter__twitter_list_members",
      "mcp__twitter__twitter_list_tweets",
      "mcp__twitter__twitter_search",
      "mcp__twitter__twitter_search_users"
    ],
    "ask": [
      "mcp__twitter__twitter_handle",
      "mcp__twitter__twitter_handle_about",
      "mcp__twitter__twitter_trends",
      "mcp__twitter__twitter_tweet",
      "mcp__twitter__twitter_tweet_replies",
      "mcp__twitter__twitter_tweet_retweeters",
      "mcp__twitter__twitter_user",
      "mcp__twitter__twitter_user_followers",
      "mcp__twitter__twitter_user_followings",
      "mcp__twitter__twitter_user_replies",
      "mcp__twitter__twitter_user_tweets",
      "mcp__twitter__check_balance",
      "mcp__twitter__topup_credits"
    ],
    "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 twitter. Review it before you use it.

Capability tags behind 3 rules
  • mcp__twitter__twitter_list_tweets untrusted-input
  • mcp__twitter__twitter_tweet_replies outbound
  • mcp__twitter__twitter_user_replies outbound

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/sh.fetcher.twitter/mcp/verify?hash=315342f8538306a79f0e8117955ad905b389479dbbea2ec699014bfebf24d43c" | jq -e '.changed == false'

Pinned hash 315342f85383, from Nov 21, 2026, 11:18 UTC.

Watch

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

https://radar.anlyon.com/servers/sh.fetcher.twitter/mcp/changes.xml

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

Badge

Anlyon Radar badge for sh.fetcher.twitter/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/sh.fetcher.twitter/mcp.svg)](https://radar.anlyon.com/servers/sh.fetcher.twitter/mcp)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

Twitter / X data for agents MCP server: questions and answers

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

Is the Twitter / X data for agents MCP server safe?

No scan can promise that. What its definitions show: 17 tools, 13 of which can change, send or delete something, and 0 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 Twitter / X data for agents MCP server delete data?

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

Can the Twitter / X data for agents MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: twitter_tweet_replies, twitter_user_replies and topup_credits.

What tools does the Twitter / X data for agents MCP server have?

17 tools: 3 irreversible, 10 write, 4 read. twitter_tweet_replies, twitter_user_replies, topup_credits, twitter_handle, twitter_handle_about, twitter_trends, twitter_tweet, twitter_tweet_retweeters and 9 more.

Does the Twitter / X data for agents MCP server need sign-in or OAuth?

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

Does the Twitter / X data for agents MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): twitter_tweet_replies and twitter_user_replies.

Has the Twitter / X data for agents MCP server changed its tools?

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