Orchyn vs TwitterAPIs
A side-by-side look at the Orchyn and TwitterAPIs MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Orchyn for social media work as a local process; choose TwitterAPIs for social media as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Orchyn when
- You need dedicated capabilities in the Social Media domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
NOOTICR_BASE_URL. - You want tools like
get_social_media, get_post_transcript, get_post_frames.
Choose TwitterAPIs when
- You need dedicated capabilities in the Social Media domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
TWITTERAPIS_KEY. - You want tools like
twitter_advanced_search, twitter_user_search, twitter_user_info.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Social Media | Social Media |
| Quality signal | 57/100 · Good | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | NOOTICR_BASE_URL | TWITTERAPIS_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 80 | 113 |
| Full listing | View Orchyn | View TwitterAPIs |
Tools & capabilities
Orchyn tools 80
get_social_mediaThe post's facts and media — contentType, title, caption, author, stats, direct media URLs, plus an inline thumbnail. Use when you want the post itself and nothing interpreted.get_post_transcriptThe words actually spoken. Where the platform publishes a caption track (TikTok, Douyin, YouTube) it is read as-is — exact rather than inferred, without processing the video; everywhere else, and where a caption track is missing, the post's own audio is transcribed on the same call (posts up to 30…get_post_framesFrames sampled evenly across a post's video, returned as **images you can actually look at** — not a description of them. ffmpeg opens the stream directly rather than downloading it, so HLS works and an expired link is re-resolved on the spot. Verified live at 3/3 on TikTok, YouTube, Instagram, Dou…get_post_commentsTop comments plus the themes the platform clusters them into, with which ones the creator pinned or liked. Use when you want to read what people wrote.analyze_post_fastThe post's transcript, caption and stats — everything but the pictures. Two fetches: `get_social_media` (1) and `get_post_transcript` (1). Use when the words and numbers answer the question.analyze_postFrames sampled across the video, as **images your model can actually look at**, plus the transcript. Two fetches: `get_post_frames` (2) and `get_post_transcript` (1). Use when the visuals are the point — framing, editing, on-screen text.understand_social_postThe same two fetches, asked for a description of what physically happens on screen rather than why it works. Use when you need the events, not the strategy.summarize_post_commentsThe comment section, every comment with a stable id, and the taxonomy to label them with — sentiment, and whether each is praise, a complaint, a bug report, a question, a request, a comparison or spam. The same `get_post_comments` call, at the same price as reading them directly. Pass `verbatim: tr…show_comment_reviewDraws the classifications your model produced — every comment with its sentiment and category, filterable and selectable. Makes no requests; it only renders what you pass it.show_post_analysisDraws the analysis your model wrote from `analyze_post`/`analyze_post_fast`/`understand_social_post` — hook strength, script structure, quotable lines, suggested hashtags and more, whichever fields you produced. Makes no requests; it only renders what you pass it.compare_social_postsThe first of two to five posts, fetched with its stats, and the comparison left to you. Fetch the rest with `get_social_media` at 1 credit each. Use when performance differs and you need to know why.show_compared_postsDraws the comparison your model wrote from `compare_social_posts` — each post scored, the winner marked, what differed and the next test worth running. Makes no requests; it only renders what you pass it.- +68 more on the listing page
TwitterAPIs tools 113
twitter_advanced_searchSearches recent tweets with X's advanced-search operators: from:, to:, since:YYYY-MM-DD, until:YYYY-MM-DD, min_faves:N, min_retweets:N, filter:links, -filter:replies, lang:en, and free text. Returns tweet text, author info, engagement metrics and a pagination cursor. product='Latest' gives chronological results; 'Top' (the default) is engagement-ranked. Example queries: 'AI agents min_faves:100', 'from:openai filter:links since:2024-01-01', '#buildinpublic -filter:replies lang:en'. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/search/tweet-advanced-searchtwitter_user_searchSearches Twitter/X user accounts by display name or handle (X's People search). Bio text is not searched, so a word that appears only in a bio returns no match. Returns matching profiles (username, display name, bio, follower count, verification status) with a pagination cursor. Covers brand handles, partial handles, and people known only by name. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/search/user-searchtwitter_user_infoReturns a user's complete public profile by @handle: display name, bio, follower count, following count, verification status, location, website, account creation date, pinned tweet, and the numeric user_id. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-infotwitter_user_info_by_idReturns a user's complete public profile by numeric user id: display name, bio, follower and following counts, verification status, location, website, account creation date and pinned tweet. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-info-by-idtwitter_user_statusReports whether a Twitter/X account is alive, suspended, or deleted. Returns a status field that is one of 'alive', 'suspended', 'not_found' or 'unavailable', plus the numeric id when the account is alive and X's own reason when it gives one. It distinguishes a suspended or deleted account from a handle that does not exist, which a profile read answers the same way. Every outcome is a successful response: the answer is in the status field, and a suspension is not an error. A protected (private) account counts as alive, since protection is a visibility setting and not an account state. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-statustwitter_user_aboutReturns a user's full 'About' object: the structured profile facts X surfaces beyond the bio, including account category and professional/business labels, verification and identity-verification flags, joined date, location and linked website, follower/following counts, and X's 'About this account' transparency panel (the account's country, how the account was created, and its username-change history). Takes a username or a user_id. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-user-abouttwitter_user_about_batchReturns the 'About' object (account country, how the account was created, username-change history, verification and the other About fields) for up to 100 accounts in one call. Takes usernames or user_ids as a comma-separated list, not both. Results come back in request order, each with an about object or an error code (not_found is billed; forbidden is free, X refuses that account to everyone; rate_limited and unavailable are free and retryable). Billed per account X answered for. One batch per API key runs at a time: a concurrent call gets 429 batch_in_progress (not billed). fields/compact apply inside each item's about object (fields=account_based_in); a results.* path returns about: {}. Cost: $0.0008 per billed item. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-user-about-batchtwitter_user_affiliatesLists the affiliated accounts of an organization profile (the smaller accounts X displays under a company's 'Affiliated' badge, e.g. employees or sub-brands). Takes a username or user_id. Returns profile data per affiliate plus a pagination cursor, and an empty list for accounts with no affiliations. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-affiliatestwitter_check_follow_relationshipReturns the follow relationship between two accounts: whether the source follows the target, whether the target follows the source, and blocking/muting flags where available. Each side is a numeric user id or a username (an unknown username or id returns a not-found error, not billed). Covers checking a follow before or after a follow action, and detecting mutuals. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-check-follow-relationshiptwitter_check_follow_relationship_batchChecks one account against up to 100 others in one call. Either one source (source_user_id or source_username) with up to 100 targets (target_usernames or target_user_ids), or one target with up to 100 sources (source_usernames or source_user_ids): a list on one side only. Each result carries the relationship from the SOURCE's side (following = source follows target, followed_by = target follows source), in request order. Example: which accounts on a shortlist already follow a brand, with the brand as target_username and the shortlist as source_usernames. Billed per pair answered with a relationship; not_found, forbidden, rate_limited and unavailable pairs are free. One batch per API key runs at a time (a concurrent call gets 429 batch_in_progress, not billed). fields/compact apply inside each item's relationship object. Cost: $0.0008 per billed item. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-check-follow-relationship-batchtwitter_audience_summarySummarises an audience in one call: samples up to 100 followers of an account (username or user_id) or retweeters of a tweet (tweet_id), reads each sampled account's About country, and returns a country histogram (shares over accounts with a known country) plus a likely-bot share from documented profile signals (default avatar, no bio, under 5 followers, extreme follow ratio, no posts, created in the last 30 days, digit-suffix handle; 3 or more signals = likely automated, a heuristic, not a verdict). Billed per item: each sample page that added accounts plus each sampled account X answered About for, so sample=100 costs at most $0.08 plus up to 3 pages. Shares the one-batch-per-key slot with the batch endpoints. Cost: $0.0008 per billed item. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-audience-summarytwitter_user_tweetsReturns a user's recent posting timeline, cursor-paginated further back. The endpoint does not filter server-side, so the response routinely includes retweets and replies alongside original posts. Every item carries is_retweet, is_reply and is_quote booleans, and author.username names who wrote it (a retweet's retweeted_tweet holds the original author). Returns tweet text, id, timestamp and engagement metrics. Cost: $0.0008 per call. Docs: https://docs.twitterapis.com/docs/reference/user-reads/user-tweets- +101 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Orchyn
{
"mcpServers": {
"orchyn": {
"command": "npx",
"args": [
"-y",
"@nooticr/mcp"
],
"env": {
"NOOTICR_BASE_URL": "YOUR_NOOTICR_BASE_URL_HERE"
}
}
}
}
TwitterAPIs
{
"mcpServers": {
"twitterapis": {
"command": "npx",
"args": [
"-y",
"@twitterapis/mcp@latest"
],
"env": {
"TWITTERAPIS_KEY": "YOUR_TWITTERAPIS_KEY_HERE"
}
}
}
}
Frequently asked questions
Orchyn is categorized under Social Media and uses a local stdio subprocess. TwitterAPIs belongs to Social Media and uses a local stdio subprocess. Pick Orchyn for social media work and TwitterAPIs for social media.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Orchyn has no declared pricing — check the project's own site. TwitterAPIs has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add orchyn and twitterapis as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Orchyn has a quality signal of 57/100 (Good) with 0 views, 0 installs and 0 GitHub stars. TwitterAPIs has 63/100 (Good) with 4 views, 0 installs and 0 GitHub stars.