SocialData
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Twitter (X) API alternative for AI agents: tweet search, profiles, followers. $0.0002 per result.
| Author | tools.socialdata |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 428 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"SocialData": {
"url": "https://api.socialdata.tools/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (14)
get_user_by_usernameread-onlyLook up a Twitter/X user profile by username (handle). Returns the profile including follower and following counts. Bills one user request against the caller's balance.
Parameters:
username(required) — string — The Twitter/X username (handle), with or without the leading @.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_by_idread-onlyLook up a Twitter/X user profile by numeric user ID. Bills one user request against the caller's balance.
Parameters:
user_id(required) — string — The numeric Twitter/X user ID, as a string (IDs exceed safe integer precision).
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
search_usersread-onlySearch Twitter/X user profiles by name or handle. Returns one page of matching profiles and bills against the caller's balance. Use this when you know roughly who someone is but not their exact handle.
Parameters:
query(required) — string — Name or handle to search for.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_tweetread-onlyFetch a single Twitter/X post by its numeric ID, including engagement counts. Bills one post request against the caller's balance.
Parameters:
tweet_id(required) — string — The numeric post ID, as a string.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_tweet_threadread-onlyFetch one page of a Twitter/X thread — the chain of follow-up posts the author wrote under their own post ("1/", "2/", ...). Give it the ID of any post in the chain and it returns that chain in order. It does NOT return what other people replied; use get_tweet_comments for those. A post the author never followed up on is a one-post thread and correctly returns just that post. Roughly 30 posts per page plus a next_cursor, so a long thread takes several calls. Each call bills against the caller's balance — do not page through a long thread unless the user asked for that.
Parameters:
tweet_id(required) — string — The numeric post ID, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_tweet_commentsread-onlyFetch one page of replies to a Twitter/X post. Returns about 20 replies plus a next_cursor. The first item of a page can repeat the last item of the previous page, so de-duplicate by post id when paging. Each call bills against the caller's balance — do not page through the whole conversation unless the user asked for that.
Parameters:
tweet_id(required) — string — The numeric ID of the post whose replies you want, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_tweetsread-onlyFetch one page of a user's own posts (excluding replies), newest first. Returns about 20 posts plus a next_cursor. If the account has a pinned post it is prepended to every page, so de-duplicate by post id when paging. Each call bills against the caller's balance — do not page through a whole timeline unless the user asked for that. Requires a numeric user ID: call get_user_by_username first if you only have a handle.
Parameters:
user_id(required) — string — The numeric Twitter/X user ID, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_tweets_and_repliesread-onlyFetch one page of a user's posts including their replies, newest first. Returns about 20 items plus a next_cursor. If the account has a pinned post it is prepended to every page, so de-duplicate by post id when paging. Each call bills against the caller's balance. Requires a numeric user ID: call get_user_by_username first if you only have a handle.
Parameters:
user_id(required) — string — The numeric Twitter/X user ID, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_mentionsread-onlyFetch one page of posts mentioning a given user, newest first. Returns about 20 posts plus a next_cursor. The first item of a page can repeat the last item of the previous page, so de-duplicate by post id when paging. Each call bills against the caller's balance.
Parameters:
username(required) — string — The Twitter/X username (handle) being mentioned, with or without the leading @.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_followersread-onlyFetch one page of a user's followers. This is one of the most expensive tools: a page is set upstream and can run to ~100 user records, every one of which is billed. Never page through a large account's followers without the user explicitly asking. Requires a numeric user ID.
Parameters:
user_id(required) — string — The numeric Twitter/X user ID whose followers you want, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_user_followingread-onlyFetch one page of the accounts a user follows. Expensive: a page is set upstream and can run to ~100 user records, every one of which is billed. Never page through a large account's following list without the user explicitly asking. Requires a numeric user ID.
Parameters:
user_id(required) — string — The numeric Twitter/X user ID whose following list you want, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
check_is_followingread-onlyCheck whether one Twitter/X user follows another. Far cheaper than fetching a follower list — use this whenever the question is about a specific pair of accounts. Both IDs must be numeric.
Parameters:
source_user_id(required) — string — The numeric ID of the user who might be following, as a string.target_user_id(required) — string — The numeric ID of the user who might be followed, as a string.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
search_tweetsread-onlySearch Twitter/X posts. Returns one page of about 20 results plus a next_cursor, and bills one search request against the caller's balance. The query supports Twitter's advanced search operators, and using them is almost always better than a bare keyword search: from:handle posts by an account to:handle replies to an account @handle posts mentioning an account #tag hashtag "exact phrase" phrase match since:2026-01-01 posts on or after a date until:2026-02-01 posts before a date min_faves:100 at least N likes min_retweets:10 at least N retweets filter:links posts containing links -filter:replies exclude replies Combine them freely: from:jack min_faves:500 since:2026-01-01
Parameters:
query(required) — string — The search query. Supports Twitter advanced search operators such as from:, to:, since:, until:, min_faves: and filter:.type— string — Latest returns the newest matching posts; Top returns the most engaged-with. Defaults to Latest.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
get_list_tweetsread-onlyFetch one page of posts from a Twitter/X list, newest first. A page is large — around 100 posts — plus a next_cursor. Billing is per result, so one call here costs several times a single-user timeline call; do not page through a busy list unless the user asked for that.
Parameters:
list_id(required) — string — The numeric Twitter/X list ID, as a string.cursor— string — Pagination cursor from a previous call's next_cursor. Omit for the first page.
Hints: read-only yes · destructive not declared · idempotent yes · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.