# io.github.kaitoInfra/twitterapi-mcp-server

> Twitter/X read-only MCP server — 12 tools: search, users, tweets, followers, timelines, trends.

- name: io.github.kaitoInfra/twitterapi-mcp-server
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.kaitoInfra%2Ftwitterapi-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.kaitoInfra%2Ftwitterapi-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "twitterapi-mcp-server": {
      "type": "http",
      "url": "https://mcp.twitterapi.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 45
- drivers: +website +reachable +uptime-97% ~updated-57d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_tweets (destructiveHint, idempotentHint); get_user_info (destructiveHint, idempotentHint); get_user_about (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 2,555 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 2,555 tokens to load them all
- tool set hash: 216388e91c075166376223113e8e5435
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.kaitoInfra/twitterapi-mcp-server.svg)](https://protogrid.dev/servers/io.github.kaitoInfra/twitterapi-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.twitterapi.io/mcp (streamable-http, auth none, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (12)

- `get_trends`: Fetch current trending topics/hashtags for a location. Pass a Yahoo Where-On-Earth ID (woeid). Common: 1=Worldwide, 23424977=USA, 23424975=UK, 23424856=Japan, 23424848=India, 23424881=South Korea. Use woeid=1 for global trends if you don't know a specific location.
- `get_tweet_quotes`: Fetch quote-tweets (tweets that quote the given tweetId). Useful for finding commentary on a tweet, measuring reach beyond direct replies. Supports time bounds (sinceTime/untilTime, Unix seconds). Paginates via cursor (~20 per page).
- `get_tweet_replies`: Fetch replies to a specific tweet. Pass the numeric tweetId of the root tweet; returns top-level replies (about 20 per page) with full tweet objects. Use this for thread analysis, sentiment on a viral post, or building reply trees.
- `get_tweet_retweeters`: Fetch users who retweeted a specific tweet (the simple 'retweet' action, not quote-tweets — for those use get_tweet_quotes). Returns user profiles with metadata. Paginates via cursor (~100 per page).
- `get_tweets_by_ids`: Batch-fetch full tweet objects by their numeric tweet IDs. Pass a comma-separated string of up to 100 IDs. Use this when you already have specific tweet IDs (e.g., from a search result, a URL, or a webhook event) and need the full tweet data — author, text, engagement counts, media, etc.
- `get_user_about`: Fetch the extended 'about' / profile page data for a Twitter/X user by screen name. Returns extra profile metadata beyond what get_user_info gives (when available). Use get_user_info first; only call this if you need additional about-page fields.
- `get_user_followers`: Fetch followers of a Twitter/X user in reverse chronological order (newest first), each with full profile metadata (name, bio, follower count, verified status, etc.). Paginates via cursor. Use this to analyze who follows an account, build follower audiences, or sample for competitive analysis. For large accounts use pagination; you will not get all followers in one call.
- `get_user_followings`: Fetch the accounts a Twitter/X user follows, with full profile metadata. Paginates via cursor. Use this to map a user's interest graph (who they follow signals what they care about).
- `get_user_info`: Fetch basic profile info for a Twitter/X user by their screen name (handle). Returns user ID, display name, bio, follower/following counts, verified status, profile picture, banner, location, website, and account creation date. Use this as the starting point for any user analysis.
- `get_user_last_tweets`: ⚠️ ONLY for 'latest / recent / what's new' queries about a user. DO NOT use for date-range queries (e.g. 'tweets from January 2026', 'tweets last week', 'tweets between X and Y', 'tweets in 2025'). For specific dates / older tweets, use **search_tweets** with query like 'from:elonmusk since:2026-01-01 until:2026-02-01'.

Fetch the MOST RECENT tweets posted by a Twitter/X user, sorted by created_at descending (newest first). Provide EITHER userName (screen name, no @) OR userId (numeric). Use userId when known — handles can change. Set includeReplies=true to include the user's reply tweets in addition to top-level tweets. Paginates via cursor (~20 per page).
- `get_user_mentions`: Fetch tweets that mention a specific Twitter/X user (i.e. tweets containing @userName). Useful for brand monitoring, sentiment tracking on a public figure, or finding conversations involving an account. Supports time-bound queries via sinceTime/untilTime (Unix seconds). Paginates via cursor.
- `search_tweets`: 🎯 PRIMARY CHOICE for date-range / historical / keyword-based tweet queries. Use this (NOT get_user_last_tweets) whenever user asks about a SPECIFIC TIME RANGE or historical tweets:
  • 'tweets from January 2026' → query='from:elonmusk since:2026-01-01 until:2026-02-01'
  • 'tweets between X and Y' → 'from:USER since:X until:Y'
  • 'tweets last week / last month' → translate to since:/until: dates
  • 'tweets containing keyword X by user Y' → 'from:Y X'
  • 'older tweets' / 'archive' / 'in 2025' → use date range, not pagination

Date format: YYYY-MM-DD (UTC midnight). 'until:' is exclusive (until:2026-02-01 = up to Jan 31).

General: Search Twitter/X for tweets matching a query. Supports the full Twitter advanced search syntax (from:, to:, since:, until:, lang:, filter:, has:, -, OR, etc). Returns ~20 tweets per page in reverse chronological order ('Latest') or by engagement ('Top'). Use this for keyword research, monitoring mentions of a brand/topic, finding tweets in a date range, or any open-ended tweet discovery.