docs, search, and execute. Native mode exposes docs plus one tool for each eligible OpenAPI operation. Active guest paid_reads keys see exactly 33 GET routes in either mode.
Modern clients negotiate MCP 2026-07-28 through server/discover. Current SDKs add required request metadata and headers.
See MCP 2026-07-28.
Native OpenAPI tools
Connect tohttps://xquik.com/mcp?codemode=false for ordinary MCP tools. Full
credentials get 119 tools. Guest keys get 34 tools.
Native tool names match OpenAPI operationId values. Schemas and contracts come
from OpenAPI. estimateExtraction is read-only and creates no job. Clients read
each generated JSON Schema from tools/list. The server embeds no model prompt,
routing table, sample count, or endpoint preference.
Use https://xquik.com/mcp for the smaller Code Mode catalog. Use native mode
when the MCP client expects one tool per operation. Binary download and credential
lifecycle operations remain REST-only in both modes.
docs
Search canonical public documentation.docs is read-only and uses no credits.
Input. Pass a non-empty query string of up to 500 characters.
search
Search the authenticated API catalog.search makes no network calls and uses no credits. Full credentials search 118 routes. Guest keys search 33 GET routes.
Input.
Sandbox code
Pass
code as an async arrow function. It is required and can be up to
10,000 characters.Spec access
The function reads
spec.paths. Each path groups its allowed HTTP methods.
OpenAPI references are resolved inline.Search by keyword
execute
Execute API calls allowed by the authenticated credential. Full account keys and OAuth tokens keep their existing account capabilities. Guest keys can execute only the 33 eligible GET reads. Authentication and required idempotency headers are injected automatically. Input.Sandbox code
Pass
code as an async arrow function. It is required and can be up to
10,000 characters.Authenticated calls
xquik is global and the function’s first argument. Authentication and required idempotency headers are injected automatically.xquik.request() resolves directly to the endpoint response body. It does not add a data or result wrapper. It sends the normalized contract automatically. Hosted MCP injects a unique Idempotency-Key for routes that require it. The sandbox reuses that key for bounded transient retries. After an unresolved write failure, verify state. Start a new attempt only when safe_to_retry is true. Responses use snake_case fields, date-time fields as Unix seconds, and structured error objects. A default REST createdAt field becomes created, while fields such as publishedAt become published_at.
Compact extraction results retain like_count, retweet_count, reply_count,
quote_count, view_count, and bookmark_count. They omit profile images and
nested enrichment.
MCP preserves every safe field that X supplies. Optional fields stay absent.
See Read Data Richness for the REST field map.
List and search responses use has_more and next_cursor, even when REST shows has_next_page or hasMore. Pass next_cursor unchanged as cursor for X reads, draws, extractions, and events. Never replace an extraction cursor with offset. Use after for /api/v1/radar and afterCursor for drafts.
Hosted MCP preserves each requested limit. REST enforces documented bounds.
Omit mode for tweet search, replies, followers, following, and verified
followers. Those operations use automatic maximum coverage. Pass
next_cursor back unchanged. Use mode=standard only for legacy pagination.
Continue through empty filtered pages while has_more is true and the cursor advances. Stop when you reach the requested total or has_more becomes false. Treat a missing or repeated next_cursor while has_more is true as stalled pagination and return the partial count plus a clear stop reason.
For advanced nested-reply diagnostics, call
/api/v1/x/tweets/<tweet_id>/replies?mode=complete&limit=25000.
Complete mode combines timelines, rankings, cursors, hidden branches, and
search. Direct replies match inReplyToId. Keep nested_replies separate.
Trust diagnostic.complete. HTTP 424 replies_incomplete preserves rows.
Inspect coveragePercentage, strategy results, cursor failures, missing
modules, recommendedFallback, and X-dependent coverage limits.
Errors use error.type, error.code, and error.message, with fields such as error.retryable or error.retry_after when available. Dependency failures use HTTP 424 in this contract. Fix validation errors before retrying, and respect retry_after on 429.
Write and media responses also use the MCP-normalized snake_case contract. Read tweet_id, write_action_id, charged_credits, media_id, media_url, and message_id from xquik.request() results. REST and generated SDK pages may show camelCase fields such as tweetId, writeActionId, chargedCredits, mediaId, and messageId; keep MCP agents on snake_case when reading tool results.
Tool output stops at 24,000 characters. Oversized output keeps its prefix and ends with [TRUNCATED]. The response stays readable, so clients can retry without a parser failure. Return fewer fields, fewer rows, or an aggregate. Use REST, SDKs, or extraction exports to persist every row.
Scope and unavailable operations
The MCP operation boundary lists excluded operations. Guest wallet credential routes and file downloads use REST. Guest keys expose only eligible paid-read GET routes. A402 creates no checkout. Report its payment_options, ask the user to choose an amount and option, then wait for explicit confirmation. Full account MCP sessions may call only an advertised account checkout action present in their catalog. Guest wallet creation and top-up remain direct REST after confirmation.
Workflow Examples.
Build and check a post draft (3-step, free)
Save a writing style from screenshots (free)
Browse trending news from radar (free)
source_format, estimated_upvotes, and x_handle. Comment bodies are not
included.
Radar + Style + Compose combined (free)
Analyze a user’s writing style
Summarize up to 100 tweets with guarded pagination (credits required)Use
q for keywords and X search operators, or pass a plain Tweet ID or X
status URL when the agent receives a single stored link.
Summarize up to 100 followers with guarded pagination (credits required)
Scrape tweet replies to CSV, JSON, or XLSX (credits required)
Post a tweet or reply with public media URLs (credits required)Hosted MCP injects the required
Idempotency-Key. Direct REST callers must
supply it themselves.
Upload media for a DM (credits required)
message_id with the uploaded media_id. Keep full DM bodies out of
shared MCP outputs; return IDs, status, media references, and source filenames
instead. Leave reply_to_message_id unset because the DM send endpoint rejects
reply threading.
Download media and get gallery link (credits required)
Bulk download: search + download combined
Monitor a user + create webhook (monitor creation requires credits, webhook is free)
Poll stored monitor events (free)
Run an extraction with a resumable handoff (credits required)
Agent handoff patterns
Use extraction exports for generated files. Keep agent handoffs small. Include the job, route, stored row IDs, next cursor, and poll action. Avoid raw pages when later workers need durable rows.Search tweets to JSON
Call
GET /api/v1/x/tweets/search with keywords, operators, a Tweet ID, or an X status URL in q. Valid time bounds apply to every page. The start is inclusive and the end is exclusive. Store tweets[].id, tweets[].text, tweets[].author, tweets[].created, has_more, next_cursor, and the original q. Cost: 1 credit per tweet returned.Scrape tweet replies to files
Call
POST /api/v1/extractions with reply_extractor and targetTweetId. The create route handles required preflight. Poll GET /api/v1/extractions/{id}, export CSV/JSON/XLSX with GET /api/v1/extractions/{id}/export, and store reply rows plus has_more and next_cursor. Cost: 1 credit per reply extracted or returned.Export followers to CRM
Call
GET /api/v1/x/users/{id}/followers or POST /api/v1/extractions with follower_explorer. Store users[].id, users[].username, users[].name, users[].followers, has_more, and next_cursor. Cost: 1 credit per follower returned or extracted.Post media tweets or replies
Call
POST /api/v1/x/tweets with media: ["https://..."]. Store tweet_id or write_action_id, reply_to_tweet_id, account, charged_credits, and the original media URLs. Cost: 30 credits text-only, plus 2 credits per started MB across attached media.Send DMs with media
Call
POST /api/v1/x/media, then POST /api/v1/x/dm/{userId} with one media_ids value. Store media_id, media_url, message_id, user_id, account, and source URL or filename. Keep full DM bodies out of shared outputs and leave reply_to_message_id unset. Cost: 10 credits per media upload plus 10 credits per DM send.Track tweet or reply writes
Call
POST /api/v1/x/tweets, then GET /api/v1/x/write-actions/{id} when pending. Store tweet_id, reply_to_tweet_id, write_action_id, status, charged, charged_credits, and media. Cost: 30 credits text-only, plus 2 credits per started MB across attached media.Monitor tweets to webhooks
Call
POST /api/v1/monitors or POST /api/v1/monitors/keywords, then POST /api/v1/webhooks. Store monitor.id, event_types, next_billing_at, webhook.id, webhook URL, and the one-time webhook.secret; run POST /api/v1/webhooks/{id}/test before routing production events. Verify X-Xquik-Signature, de-dupe production payloads with deliveryId and streamEventId, and inspect GET /api/v1/webhooks/{id}/deliveries for retry status rows. Each payload contains one monitor event, so process multiple POSTs when one check catches multiple new matching tweets. Cost: 21 credits per active monitor-hour; webhook delivery is included.Replay monitor events
Call
GET /api/v1/events when a receiver missed webhook delivery or a downstream queue needs replay. Store event_id, type, monitor_id, monitor_type, occurred_at, has_more, and next_cursor. Use cursor for the next page.POST /api/v1/x/tweets rejects media_ids with 400 unsupported_field; pass up to 4 public image URLs or exactly 1 public MP4 video URL up to 100 MB in media instead. Reserve uploaded media_id values for direct messages.
Look up known tweet IDs
GET /api/v1/x/tweets is available in both the full and paid_reads catalogs. Send at most 100 tweet IDs.
Subscribe (free, returns checkout or billing portal URL)Run this mutation only after the user explicitly asks to subscribe or open billing.
API endpoints
The REST API documents 129 operations. The full MCP catalog exposes 118 across 10 categories:Account, composition, and credits
20 MCP operations across
account, composition, and credits: account info, subscribe, X identity, compose, styles, drafts, radar, balance checks, checkout creation, and checkout status.Extractions and media
9 operations across
extraction and media: giveaway draws, extraction jobs, estimates, and media download.Monitoring and webhooks
19 operations in
monitoring: account monitors, keyword monitors, stored events, webhooks, deliveries, and test delivery.Support
5 operations in
support: create, list, read, reply, and close tickets.Tweets, profiles & followers
38 operations in
twitter: batch and single tweet lookup, tweet search, article lookup, user lookup, follow checks, trends, bookmarks, notifications, timeline, DM history, likes, media, followers, replies, communities, and lists.X accounts and writes
27 operations across
x-accounts and x-write: connect accounts, resolve challenges, post tweets, like, retweet, follow, remove followers, send DMs, upload media, update profiles, and manage communities.search to query all 118 catalog routes and their response shapes.
With a guest paid_reads key, search and execute expose exactly 33 twitter GET operations. The docs tool remains available. Use the guest paid-read route inventory as the public route list.
Cost summary
Always free discovery
docs and search are free. They return documentation and API contract details.Free account and stored records
Compose, cached styles, drafts, radar, subscribe, account, support, credits, X account management, webhooks, stored monitors, stored events, and existing extraction or draw reads are free.
Metered reads and jobs
Tweet search, user lookup, follow checks, media download, trends, extraction creation, and draw creation are metered.
Monitor billing
Active monitors cost 21 credits per monitor-hour. Creating one requires enough available credits.
Write actions
Tweet, reply, like, retweet, follow, DM, profile, community, and media upload writes are metered.
Metered refreshes
Fresh style analysis after the 7-day cache window requires enough available credits.
Error handling
- 402 /
no_subscription/subscription_inactive. Report the billing state and available account actions. Existing available credits can still fund metered calls. Ask the user to choose and confirm before callingPOST /api/v1/subscribe. - 402 /
no_credits/insufficient_credits. Reportpayment_options. Full account sessions may create account checkout after confirmation. Guest sessions may explain the direct REST top-up flow, but MCP cannot execute it. - 429 /
rate_limit_exceeded. Respecterror.retry_after, then retry safe reads with backoff. - 424 dependency errors. Report
error.code, preserve partial aggregates, and retry only whenerror.retryableallows it. - Validation errors. Fix the path, query, or body before retrying.