twitter MCP server
com.jojapi/twitterjojapi.comstreamable-httpv1.0.0Scanned
X (formerly Twitter): X (formerly Twitter) public and private data API for search, posts (Tweets).
32 tools: 32 only read.
- Reads private data · 2
- Reads text others write · 9
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 twitter MCP server can do
The twitter MCP server is published by jojapi.com, a domain the MCP Registry verified. It has 32 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
2 tools read private data (get_v2_TweetDetail and get_email_search_by_username); 9 tools bring in text other people can write (get_v2_TweetDetail, get_v2_Tweet, get_v2_Favoriters and 6 more); 1 tool can send data out of your system (get_ShortUrl). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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 18, 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.
32 tools
Only reads 32Show 32 read-only tools
get_AutoCompleteAuto Complete Group: Explore.No findings
Why it is in this group
- The name "get_AutoComplete" says "get": a word for reading.
Description, as the server wrote it Auto Complete Group: Explore. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_email_search_by_usernameEmail Search (by username) Group: User.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_email_search_by_username" says "get": a word for reading.
What it can reach
- private-dataThe name "get_email_search_by_username" says "get" and "email": it reads mail.
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe name "get_email_search_by_username" says "get" and "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it Email Search (by username) Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_SearchSearch Group: Explore.No findings
Why it is in this group
- The name "get_Search" says "get": a word for reading.
Description, as the server wrote it Search Group: Explore. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_ShortUrlTwitter URL shortening service Group: Misc.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_ShortUrl" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_ShortUrl" says "get" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Twitter URL shortening service Group: Misc. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_FollowersUser Followers / Light Group: User.No findings
Why it is in this group
- The name "get_v1_1_Followers" says "get": a word for reading.
Description, as the server wrote it User Followers / Light Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_FollowersIdsUser Followers IDs Group: User.No findings
Why it is in this group
- The name "get_v1_1_FollowersIds" says "get": a word for reading.
Description, as the server wrote it User Followers IDs Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_FollowingUser Following / Light Group: User.No findings
Why it is in this group
- The name "get_v1_1_Following" says "get": a word for reading.
Description, as the server wrote it User Following / Light Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_FollowingIdsUser Following IDs Group: User.No findings
Why it is in this group
- The name "get_v1_1_FollowingIds" says "get": a word for reading.
Description, as the server wrote it User Following IDs Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_HashflagsHashflags Group: Misc.No findings
Why it is in this group
- The name "get_v1_1_Hashflags" says "get": a word for reading.
Description, as the server wrote it Hashflags Group: Misc. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_LocationsLocations Group: Explore.No findings
Why it is in this group
- The name "get_v1_1_Locations" says "get": a word for reading.
Description, as the server wrote it Locations Group: Explore. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_TranslateProfileTranslate Profile Group: User.No findings
Why it is in this group
- The name "get_v1_1_TranslateProfile" says "get": a word for reading.
Description, as the server wrote it Translate Profile Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_TranslateTweetTranslate Tweet Group: Tweet.Reads text others writeNo findings
Why it is in this group
- The name "get_v1_1_TranslateTweet" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_v1_1_TranslateTweet" says "get" and "tweet": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it Translate Tweet Group: Tweet. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_TrendsTrends Group: Explore.No findings
Why it is in this group
- The name "get_v1_1_Trends" says "get": a word for reading.
Description, as the server wrote it Trends Group: Explore. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v1_1_UsersGet Users Group: User.No findings
Why it is in this group
- The name "get_v1_1_Users" says "get": a word for reading.
Description, as the server wrote it Get Users Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_FavoritersTweet Favoriters Group: Tweet.Reads text others writeNo findings
Why it is in this group
- The name "get_v2_Favoriters" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it Tweet Favoriters Group: Tweet. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_FollowersUser Followers Group: User.No findings
Why it is in this group
- The name "get_v2_Followers" says "get": a word for reading.
Description, as the server wrote it User Followers Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_FollowingUser Following Group: User.No findings
Why it is in this group
- The name "get_v2_Following" says "get": a word for reading.
Description, as the server wrote it User Following Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_LikesUser Likes Group: User.No findings
Why it is in this group
- The name "get_v2_Likes" says "get": a word for reading.
Description, as the server wrote it User Likes Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_ListTimelineList Timeline Group: List.No findings
Why it is in this group
- The name "get_v2_ListTimeline" says "get": a word for reading.
Description, as the server wrote it List Timeline Group: List. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_RetweetersTweet Retweeters Group: Tweet.Reads text others writeNo findings
Why it is in this group
- The name "get_v2_Retweeters" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it Tweet Retweeters Group: Tweet. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_SubscriptionsUser Subscriptions Group: User.No findings
Why it is in this group
- The name "get_v2_Subscriptions" says "get": a word for reading.
Description, as the server wrote it User Subscriptions Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_TweetTweet Detail / Alternative Group: Tweet.Reads text others writeNo findings
Why it is in this group
- The name "get_v2_Tweet" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_v2_Tweet" says "get" and "tweet": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it Tweet Detail / Alternative Group: Tweet. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_TweetDetailTweet Detail & Conversation Group: Tweet.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_v2_TweetDetail" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "conversation": it reads messages.
- untrusted-inputThe name "get_v2_TweetDetail" says "get" and "tweet": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it Tweet Detail & Conversation Group: Tweet. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserAffiliatesUser Affiliates Group: User.No findings
Why it is in this group
- The name "get_v2_UserAffiliates" says "get": a word for reading.
Description, as the server wrote it User Affiliates Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserByRestIdUser By Rest ID Group: User.No findings
Why it is in this group
- The name "get_v2_UserByRestId" says "get": a word for reading.
Description, as the server wrote it User By Rest ID Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserByScreenNameUser By Screen Name Group: User.No findings
Why it is in this group
- The name "get_v2_UserByScreenName" says "get": a word for reading.
Description, as the server wrote it User By Screen Name Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserHighlightsUser Highlights Group: User.No findings
Why it is in this group
- The name "get_v2_UserHighlights" says "get": a word for reading.
Description, as the server wrote it User Highlights Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserMediaUser Media Group: User.No findings
Why it is in this group
- The name "get_v2_UserMedia" says "get": a word for reading.
Description, as the server wrote it User Media Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UsersByRestIdsUsers By Rest IDs Group: User.No findings
Why it is in this group
- The name "get_v2_UsersByRestIds" says "get": a word for reading.
Description, as the server wrote it Users By Rest IDs Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserTweetsUser Tweets Group: User.Reads text others writeNo findings
Why it is in this group
- The name "get_v2_UserTweets" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_v2_UserTweets" says "get" and "tweet": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it User Tweets Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_UserTweetsAndRepliesUser Tweets & Replies Group: User.Reads text others writeNo findings
Why it is in this group
- The name "get_v2_UserTweetsAndReplies" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_v2_UserTweetsAndReplies" says "get" and "tweet": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "tweet": it reads posts, which other people can write.
Description, as the server wrote it User Tweets & Replies Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API key).
get_v2_VerifiedFollowersUser Verified Followers Group: User.No findings
Why it is in this group
- The name "get_v2_VerifiedFollowers" says "get": a word for reading.
Description, as the server wrote it User Verified Followers Group: User. Billing per call: 1 Credits. Agents can pay per call ($0.01 via x402/MPP, no API 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.
18 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__twitter__get_ShortUrl"
]
}
}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.
Looked at Nov 20, 2026, 19:31 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
- 0
- 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
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://mcp.jojapi.com/twitterclaude mcp add --transport http twitter https://mcp.jojapi.com/twitterRun 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.
{
"permissions": {
"allow": [
"mcp__twitter__get_AutoComplete",
"mcp__twitter__get_Search",
"mcp__twitter__get_v1_1_Trends",
"mcp__twitter__get_v1_1_Locations",
"mcp__twitter__get_v2_TweetDetail",
"mcp__twitter__get_v2_Tweet",
"mcp__twitter__get_v2_Favoriters",
"mcp__twitter__get_v2_Retweeters",
"mcp__twitter__get_v1_1_TranslateTweet",
"mcp__twitter__get_email_search_by_username",
"mcp__twitter__get_v1_1_Users",
"mcp__twitter__get_v2_UserByScreenName",
"mcp__twitter__get_v2_UserByRestId",
"mcp__twitter__get_v2_UsersByRestIds",
"mcp__twitter__get_v2_UserTweets",
"mcp__twitter__get_v2_UserTweetsAndReplies",
"mcp__twitter__get_v2_UserMedia",
"mcp__twitter__get_v2_Likes",
"mcp__twitter__get_v2_Followers",
"mcp__twitter__get_v1_1_Followers",
"mcp__twitter__get_v1_1_FollowersIds",
"mcp__twitter__get_v2_VerifiedFollowers",
"mcp__twitter__get_v2_Following",
"mcp__twitter__get_v1_1_Following",
"mcp__twitter__get_v1_1_FollowingIds",
"mcp__twitter__get_v2_Subscriptions",
"mcp__twitter__get_v2_UserAffiliates",
"mcp__twitter__get_v2_UserHighlights",
"mcp__twitter__get_v1_1_TranslateProfile",
"mcp__twitter__get_v1_1_Hashflags",
"mcp__twitter__get_v2_ListTimeline"
],
"ask": [
"mcp__twitter__get_ShortUrl"
],
"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 9 rules
- mcp__twitter__get_v2_TweetDetail private-data, untrusted-input
- mcp__twitter__get_v2_Tweet untrusted-input
- mcp__twitter__get_v2_Favoriters untrusted-input
- mcp__twitter__get_v2_Retweeters untrusted-input
- mcp__twitter__get_v1_1_TranslateTweet untrusted-input
- mcp__twitter__get_email_search_by_username private-data, untrusted-input
- mcp__twitter__get_v2_UserTweets untrusted-input
- mcp__twitter__get_v2_UserTweetsAndReplies untrusted-input
- mcp__twitter__get_ShortUrl untrusted-input, 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/com.jojapi/twitter/verify?hash=ab2d8af39abd06a46c3f2911796a246b3c570741d05c29e7460c30203c7bfd78" | jq -e '.changed == false'Pinned hash ab2d8af39abd, from Nov 18, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.jojapi/twitter/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.jojapi/twitter)Source: MCP Registry. Synced Oct 21, 2026, 17:57 UTC.
twitter MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the twitter MCP server safe?
- No scan can promise that. What its definitions show: 32 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the twitter 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 MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the twitter MCP server have?
- 32 tools: 32 read. get_AutoComplete, get_Search, get_v1_1_Trends, get_v1_1_Locations, get_v2_TweetDetail, get_v2_Tweet, get_v2_Favoriters, get_v2_Retweeters and 24 more.
Does the twitter MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the twitter MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_ShortUrl.
Has the twitter MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.