Skip to main content
Glama

x-use — MCP server for X (Twitter)

x-use logo — research, draft, review and publish with an MCP server for X (Twitter)

Connect your AI client to X research, inbox reads, and reviewed publishing.

x-use is an open-source Python Model Context Protocol (MCP) server and CLI for X (Twitter). Connect Claude, Codex, Cursor or another local MCP client to profile research, inbox management and reviewed publishing. It uses your authenticated browser session, supports multiple accounts and runs locally without official X API credentials.

PyPI Python CI MIT license GitHub stars

Quickstart · Documentation · Tool reference · Discussions · Contribute

What can you do with x-use?

  • Research before replying: search X, inspect a profile, read posts and bounded thread context, and prepare a relevant reply.

  • Work through your inbox: inspect visible conversations, unread messages, requests and notifications; prepare individual messages and supported conversation actions for review.

  • Publish with context: stage posts or multi-post threads, inspect the exact text, and approve the draft when it is ready.

  • Organize outreach locally: maintain leads, opt-outs and campaign drafts with per-account limits and delivery tracking.

Your AI client supplies the reasoning and text. An optional OpenAI-compatible LLM configuration supports server-side generation; ordinary explicit-text MCP workflows do not need that extra key.

Related MCP server: Spectre

Quickstart

Requires Python 3.11.5+ and Chromium. The CI matrix covers Python 3.11–3.14 on Windows, macOS and Linux.

Version 3.3.0 provides 82 tools for research, inbox management, reviewed publishing and account operations. Upgrade the package and restart your MCP client to load the current tools.

1. Install the server and browser

python -m pip install --upgrade x-use-mcp
python -m patchright install chromium

2. Choose a private data directory and initialize

Windows PowerShell:

$env:X_USE_HOME = "$env:LOCALAPPDATA\x-use"
x-use init
x-use doctor

macOS / Linux:

export X_USE_HOME="$HOME/.local/share/x-use"
x-use init
x-use doctor

The wizard configures your account and imports your own X session cookies from a local JSON export. Keep cookies and inbox PINs private. Use the same absolute data directory in your client configuration below; shell environment settings alone do not configure a desktop client.

3. Connect your MCP client

Use this stdio configuration in clients that accept an mcpServers object, such as Claude Desktop:

{
  "mcpServers": {
    "x-use": {
      "command": "/absolute/path/to/x-use",
      "args": ["mcp"],
      "env": {
        "X_USE_HOME": "/absolute/path/to/x-use-data"
      }
    }
  }
}

Replace both paths. On Windows, use the installed x-use.exe path and forward slashes in JSON, for example C:/Users/you/AppData/Local/x-use for the data directory. Locate the executable with Get-Command x-use in PowerShell or command -v x-use on macOS/Linux.

Claude Code, Codex, Cursor and Windsurf have their own registration locations or commands. Follow the client setup instructions, then reload the client if required. Ask it to call list_accounts before starting browser work.

4. Try a first workflow

With draft mode enabled, ask your client:

Check my account health, research the profile I specify, and summarize its recent visible posts. Prepare one relevant reply draft and show me its ID and exact text. Wait for my approval before publishing.

The flow is get_account_health → get_profile_context → prepare_reply → reply_to_tweet → get_draft. The reply tool stages a draft under the default policy; prepare_reply supplies context. Use approve_draft only when authorized.

More workflow examples cover inbox triage, outreach and threads.

git clone https://github.com/ihuzaifashoukat/x-use.git
cd x-use
python scripts/setup_uv.py --dev

On Windows you can use py -3 scripts/setup_uv.py --dev; on macOS/Linux use python3 if needed. Setup installs uv when missing, synchronizes locked dependencies into .venv, installs matching Chromium, creates missing sample configuration and runs diagnostics. Activate the environment or use its executable directly. Then initialize your account.

For assisted installation, use the setup prompt or install the root setup skill:

npx skills add ihuzaifashoukat/x-use

The Claude Code plugin includes the bundled skills and MCP configuration guidance.

Capabilities

Workflow

Representative tools

Details

Profile and post research

get_profile_context, search_profile, search_tweets, get_tweet, get_thread

Visible profile, post, media and bounded thread evidence

Inbox and notifications

get_inbox, search_conversations, get_conversation, get_notifications

Inbox/request folders, read-state evidence and partial message history

Publishing and inbox controls (3.1.0)

get_bookmarks, edit_tweet, delete_tweet, unfollow_profile, manage_conversation

Reviewed changes; supported controls and limitations

Reviewed publishing

post_tweet, reply_to_tweet, prepare_thread, approve_draft

Persistent drafts and resumable thread progress

Individual outreach

prepare_outreach, send_message, follow_profile

Message and follow drafts require individual approval

Leads and campaigns

upsert_lead, create_campaign, prepare_campaign_messages, opt_out_lead

Local records, suppression and bounded batches

Account readiness (3.1.0)

get_account_health, get_session_status, test_proxy

Operational score, evidence and recovery advice, plus explicit proxy connectivity checks

Scheduling and recovery

queue_post, process_queue, get_account_health, resolve_action_outcome

Durable budgets, explicit recovery and uncertain-outcome tracking

Version 3.3.0 includes 82 tools, seven prompts, four resource patterns and seven bundled skills. 3.1.0 added runtime diagnostics, campaign previews, bookmarks, reviewed post edits/deletions, engagement reversal and inbox controls to the 70 tools in 3.0.0; 3.3.0 adds quote posts to post_tweet and keeps the same tool set. See publishing and inbox controls for supported layouts and testing limits.

The MCP guide documents every tool, prompt and resource. Validation evidence separates local protocol checks, synthetic browser fixtures and authorized live-account checks.

For a uvx client, use uvx x-use-mcp or pin the release with uvx x-use-mcp==3.3.0. The x-use-mcp executable starts MCP without arguments; the existing x-use mcp command remains supported. Clients pinned to 3.0.0 must use uvx --from x-use-mcp==3.0.0 x-use mcp.

How execution works

The current MCP runtime uses async Patchright Chromium with separate account contexts. Your configuration, cookies, drafts, queue and action journals live under X_USE_HOME. AI-client and optional model-provider data handling depends on the client and provider you choose.

The protocol implementation uses the MCP Python SDK v2 line (mcp>=2.3,<3). It negotiates handshake protocol versions 2024-11-05 through 2025-11-25 with existing clients.

Draft mode is enabled by default for ordinary publishing. Messages, follows and thread starts require draft approval. Direct publishing mode, explicit queue processing, opt-in auto-drain and the legacy batch runner have separate execution paths. Review the configuration reference before changing these settings.

The development checkout allows one MCP server process per X_USE_HOME, preventing concurrent servers from using stale draft and queue state. Close the existing connection before opening the same data directory in another client.

Limits to understand

  • Browser reads are bounded by visible X content. Followers, inboxes and threads are not complete exports; unavailable evidence remains unknown.

  • Opening conversations or notifications can change their native read state.

  • Encrypted inboxes may need the account owner's PIN again after a browser-context restart.

  • Analytics currently reports availability and the observed Premium gate; it does not provide a complete analytics dashboard.

  • X layout changes, expired sessions, account challenges and platform limits can interrupt work. Local controls do not guarantee protection from account restrictions.

  • The legacy Selenium batch engine (x-use run / run_cycle) executes separately from MCP draft review. Community posting is not currently verified in the async runtime.

See browser behavior and recovery and responsible-use guidance.

Frequently asked questions

Does x-use require an X API key?

No. It operates visible X pages through a browser authenticated with your session cookies. It does not require official X API credentials. Optional server-side text generation may require an LLM provider key.

Which MCP clients can use x-use?

Clients that launch local stdio MCP servers can use x-use. Setup examples cover Claude Desktop, Claude Code, Codex, Cursor and Windsurf. Client-specific discovery and reload behavior varies.

Does x-use automatically send every drafted message?

No. Message drafts require individual approval. Other write behavior depends on draft mode, queue execution and the legacy runner; check the configured policy before requesting actions.

Can I manage multiple X accounts?

Yes. Accounts have separate cookies, browser contexts and policy settings, with optional proxy routes. Browser capacity is bounded and depends on your host and configuration.

Can I edit posts or manage my X inbox?

Version 3.1.0 added reviewed edits and deletion of your own posts, bookmarks, unfollowing, and supported conversation request, mute/unmute and deletion actions. X determines edit eligibility. Inbox history is partial, and per-message editing/deletion, attachment sending and group administration are not implemented. See the controls guide for exact arguments and limits.

Is x-use free and open source?

The project is MIT licensed with no project license fee. AI-client subscriptions, optional model providers, proxies and hosting may have their own costs.

Is x-use affiliated with X?

No. x-use is an independent community project. X and Twitter are names used to identify the platform it works with.

Was this project called twitter-automation-ai?

Yes. The project was renamed to x-use during the v2 relaunch. See the changelog for its history.

Documentation and community

Start with the documentation index. It links setup, workflows, tools, configuration, presets, architecture and troubleshooting. X-Use is maintained by Huzaifa Shoukat and welcomes community contributions.

Found a reproducible problem? Report a bug. Have a workflow to share? Start a discussion. Useful first contributions include clearer setup instructions, fictional browser fixtures, platform fixes and example presets.

See CONTRIBUTING, the Code of Conduct and security policy. If x-use helps your work, a GitHub star helps other developers discover it.

Star history

License

MIT.

Available Tools

82 tools
add_accountA

Add an account to config/accounts.json (validated, backed up, atomic). cookie_file is a path ON THIS MACHINE to an exported x.com cookies JSON; it is validated and copied beside the selected accounts configuration as <account_id>_cookies.json. Cookie values never pass through the tool call. persona is freeform markdown describing the account's voice/engagement style (max 4000 chars).

Inputs: account_id (required), proxy, persona, is_active, +2 more. Returns: result

add_campaign_leadsA
Idempotent

Add 1-100 local leads from this account to a campaign. Repeated ids are ignored. The whole batch fails if any id belongs to another account. Adding a lead does not make an opted-out or closed lead eligible.

Inputs: account (required), lead_ids (required), campaign_id (required). Returns: result

add_proxyA
Idempotent

Add a proxy URL to a named pool (created if new) in settings.json. Validated, deduped, backed up, atomic. Credentials are masked in the response. Assign it to accounts via update_account(proxy="pool:") or a direct URL.

Inputs: pool (required), proxy_url (required). Returns: result

approve_draftA
Destructive

Execute a pending draft created by a write tool. Runs the exact same execution path as direct mode (pacing, dedup, metrics). A draft can be approved exactly once; unknown or consumed ids return an error.

Inputs: draft_id (required). Returns: result

bookmark_tweetA

Prepare a bookmark draft for one exact post. Always requires approve_draft.

Inputs: account (required), tweet_url (required). Returns: object

cancel_queued_actionA
Idempotent

Cancel a pending or failed queued action. Done, processing, and already-cancelled items cannot transition.

Inputs: queue_id (required). Returns: result

cancel_threadA
Idempotent

Cancel remaining thread segments locally. Retains confirmed URLs and uncertain evidence; never deletes posts or clears safety uncertainty. An active send must finish before cancellation can be accepted.

Inputs: run_id (required). Returns: result

close_sessionB
Idempotent

Close one account's browser context; retain the operator's cookie file.

Inputs: account (required). Returns: object

continue_threadA

Resume an approved run only at a known unsubmitted segment after spacing/budget/preflight recovery. Uncertain segments are never resent.

Inputs: run_id (required). Returns: result

create_campaignA

Create a local draft campaign. Personalize using {handle}, {name}, {display_name}, or {company}; include a recipient name/handle placeholder. {name} falls back to @handle. Notes cannot be templated. Nothing sends.

Inputs: name (required), account (required), message_template (required). Returns: result

delete_tweetA

Prepare permanent deletion of your own exact post. Supply its current text (empty for media-only). Always requires approve_draft; cannot be undone.

Inputs: account (required), tweet_url (required), expected_text (required). Returns: object

draft_post_variationsA

Generate count distinct takes on a topic with the server-side LLM (persona-aware) and stage each as a post DRAFT. Nothing is posted, approve one and reject the rest. Requires the 'llm' block in settings.

Inputs: topic (required), account (required), count. Returns: result

edit_tweetA

Prepare a text edit of your own post. Supply its current exact text and replacement; configure self_handles. X must expose Edit post; eligibility/time limits apply. Always requires approval. Media replacement is unsupported.

Inputs: text (required), account (required), tweet_url (required), expected_text (required). Returns: object

engageA

Engage with tweets found via keyword search. actions is a subset of ["like", "retweet"] (default ["like"]); every candidate passes the analyzer relevance gate; max_actions is hard-capped by the account's per-run config caps. In draft mode (default) each planned action becomes an individually approvable draft and nothing executes.

Inputs: account (required), keywords (required), actions, max_actions. Returns: result

follow_profileA

Prepare a follow draft for one X profile; approve_draft performs the action.

Inputs: account (required), profile (required). Returns: object

generate_and_postA

Generate a post about topic with the configured LLM and post it. In draft mode (default) the generated text is stored in the draft's payload/preview so a human reviews the actual content before anything is posted.

Inputs: topic (required), account (required). Returns: result

get_accountA
Read-only

Show one account's masked config (no cookies, no password, proxy credentials masked) plus cookie-file status. Read-only, never starts a browser.

Inputs: account (required). Returns: result

get_account_analyticsB
Read-only

Read the signed-in owner's X analytics availability. Requires X Premium when the observed paywall says so; unsupported layouts return no metrics. Distinct from local action metrics and public post counts.

Inputs: account (required), limit. Returns: object

get_account_healthA
Read-only

Read-only health snapshot for one account: config presence, cookie-file validity, metrics counters, warm-session state, queue depth, pending drafts, and a transparent local readiness score out of 100. Unknown evidence earns no points; this does not predict X enforcement or establish live authentication. Never starts a browser. A config that fails validation is REPORTED (config.valid=false with the error), not raised, surfacing that is the point of a health check.

Inputs: account (required). Returns: result

get_account_safetyC
Read-only

Read local limits, pause reason, and writes needing outcome reconciliation.

Inputs: account (required). Returns: object

get_bookmarksA
Read-only

Read bounded posts in the default bookmarks feed. Partial results; bookmark folders are not traversed.

Inputs: account (required), limit. Returns: object

get_campaignC
Read-only

Read this account's campaign and a membership page. limit 1-100; members_next_offset identifies the next page of local outcomes.

Inputs: account (required), campaign_id (required), limit, offset. Returns: result

get_campaign_summaryB
Read-only

Read local membership/delivery counts and opt-out suppression count. These are recorded outcomes; this tool never checks X or sends work.

Inputs: account (required), campaign_id (required). Returns: result

get_conversationC
Read-only

Read bounded visible conversation context and observed request/reply state. Cursor stays within the visible window; opening may clear X unread state. Does not accept requests.

Inputs: account (required), conversation_id (required), limit, before_message_id. Returns: object

get_conversation_controlsC
Read-only

Inspect visible request and conversation-menu controls. Opening may mark read; unsupported layouts return an error, never guessed capabilities.

Inputs: account (required), conversation_id (required). Returns: object

get_draftA
Read-only

Show one draft by id. Read-only.

Inputs: draft_id (required). Returns: result

get_home_feedB
Read-only

Read posts currently visible in the home feed; no engagement actions.

Inputs: account (required), limit. Returns: object

get_inboxB
Read-only

Read visible inbox/requests/other summaries with all/unread/read filtering. Native Unread selection is verified when available; never opens or accepts a conversation.

Inputs: account (required), limit, folder, inbox_filter, +1 more. Returns: object

get_leadB
Read-only

Read one local lead belonging to this account, including its notes.

Inputs: account (required), lead_id (required). Returns: result

get_metricsA
Read-only

Read recorded metrics for an account (counters + recent events). Read-only, never starts a browser.

Inputs: account (required). Returns: result

get_notificationsB
Read-only

Read bounded visible X notifications from a verified All or Mentions tab.

Reports observed actors, related posts, type evidence and unread state; absent evidence remains unknown. Visiting this view may mark X notifications read. Results cover only the visible supported UI.

Inputs: account (required), view, limit. Returns: object

get_profileC
Read-only

Read public profile details using visible X page elements.

Inputs: account (required), profile (required). Returns: object

get_profile_connectionsB
Read-only

Read visible public followers/following. This is not a private address book or complete contact export.

Inputs: account (required), profile (required), limit, relationship. Returns: object

get_profile_contextB
Read-only

Preferred outreach read: exact profile details and bounded authored posts together. No draft or send.

Inputs: account (required), profile (required), post_limit. Returns: object

get_profile_postsB
Read-only

Read one author's posts, posts-and-replies, or media tab. feed: posts|replies|media. Results are bounded and partial.

Inputs: account (required), profile (required), feed, limit. Returns: object

get_run_statusA
Read-only

Poll run_cycle handles. With run_id omitted, lists every run started since this server booted. Read-only.

Inputs: run_id. Returns: result

get_runtime_infoA
Read-only

Inspect server/package versions, tool count and configured execution mode, backend workflow support and effective unlock allowance without starting a browser. Contains no credentials, paths, account identities or raw environment values. Configuration does not prove live X authentication; use get_account_health and a bounded read for that.

Inputs: no named parameters. Returns: result

get_session_statusA
Read-only

Inspect local session lifecycle (cold/starting/ready/busy/closing/ disconnected/closed) without reading cookies or starting a browser. Ready means locally usable transport, not verified live X authentication. Legacy backends may report unknown for a warm session.

Inputs: account. Returns: object

get_threadA
Read-only

Read bounded visible conversation context around one exact X post. Includes ordered posts and media metadata; parent links remain unknown unless the page proves them. Results are partial, not a full archive. include_images attaches at most five photos/video posters with source mappings for YOUR model to analyze; no server LLM or video transcription. Read this before composing contextual replies or reply threads.

Inputs: tweet_url (required), limit, account, include_images. Returns: object

get_thread_runC
Read-only

Read durable local segment states, exact published URLs and next index.

Inputs: run_id (required). Returns: result

get_tweetA
Read-only

Read-only fetch of one tweet: text, author, public counts, typed media (photos + video posters) and the account's persona. With include_images=true (default) photos also attach as image content so a vision-capable client sees them; the envelope always carries URLs

  • alt text as the fallback. Nothing is posted; draft mode N/A.

Inputs: account (required), tweet_url (required), include_images. Returns: object

list_accountsA
Read-only

List configured accounts with secrets stripped (no cookies, no passwords, proxy credentials masked). Read-only, never starts a browser.

Inputs: no named parameters. Returns: result

list_campaignsB
Read-only

List this account's local campaigns (without membership details). Status: draft, ready, paused, completed. limit 1-100, with offset.

Inputs: account (required), limit, offset, status. Returns: result

list_draftsA
Read-only

List drafts, newest first. status filters to one of pending/approved/partial/executed/failed/rejected/uncertain; account filters by account id; limit caps the response (max 100). Read-only.

Inputs: limit, status, account. Returns: result

list_leadsA
Read-only

List this account's local leads, optionally filtering by status or exact tag. limit 1-100; offset supports pagination. No browser starts.

Inputs: account (required), tag, limit, offset, +1 more. Returns: result

list_proxiesA
Read-only

List proxy pools (size, masked members, rotation cursor), the global pool strategy, each account's assignment, and the global fallback proxy. Read-only, never starts a browser.

Inputs: no named parameters. Returns: result

list_queueA
Read-only

List queued actions with their full payloads (exactly what will fire), plus per-status counts. limit 1-100; offset pages through local history. Read-only, never starts a browser.

Inputs: limit, offset, status, account. Returns: result

manage_conversationA

Draft one inbox action: accept a request, mute/unmute notifications, or delete a conversation from your inbox. Delete cannot be undone locally and does not promise deletion for recipients. Always requires approval; only verified visible controls are supported.

Inputs: account (required), operation (required), conversation_id (required). Returns: object

opt_out_leadB
Idempotent

Permanently suppress outreach to this account's lead handle. This blocks prepared campaign deliveries as well as future drafts.

Inputs: account (required), lead_id (required). Returns: result

pause_account_actionsA
Idempotent

Pause browser actions durably until the operator explicitly resumes them.

Inputs: account (required). Returns: object

post_tweetB

Post a tweet from an account. media = local file paths; community = target community id; quote_tweet_url = post it as a quote of that tweet, with the text and media in the quote (async browser backend). In draft mode (default) returns a draft for review and posts nothing; approve_draft(draft_id) executes it.

Inputs: text (required), account (required), media, community, +1 more. Returns: result

prepare_campaign_messagesA

Prepare at most 20 personalized private-message drafts for eligible new/qualified leads on an active account. Skip opt-outs and prior pending/delivered members. Preparation marks the campaign ready; review every exact payload and approve each draft individually. No bulk sends, browser, scraping, or LLM call occurs, even when draft_mode is off.

Inputs: account (required), campaign_id (required), max_messages. Returns: result

prepare_outreachA

Fetch profile details and up to 10 authored posts, then prepare ONE local DM draft with your exact supplied text. Use get_profile_context to research and write a personalized message first. Context is a bounded visible subset; it is not a complete post history. No server LLM or message send occurs. Review the returned recipient, context and draft, then approve_draft individually; draft_mode does not bypass review. Opt-outs and account activation are rechecked after the browser read.

Inputs: account (required), profile (required), message_text (required), post_limit. Returns: object

prepare_replyA
Read-only

Read-only reply context: the tweet's text AND media (photos attach as image content so your model can see them), plus the account's keywords and persona. YOUR model writes the reply itself, no server-side LLM, nothing posted. Then pass your text to reply_to_tweet(text=...) or queue_engagement(action="reply", text=...).

Inputs: account (required), tweet_url (required), include_images. Returns: object

prepare_threadA

Stage 1-20 exact text/media posts for review; always creates a draft. Optional reply_to starts a reply thread. Every later post replies to the immediately preceding confirmed new post. No LLM is called.

Inputs: posts (required), account (required), reply_to. Returns: result

preview_campaign_messageA
Read-only

Preview one campaign member's exact personalized message and local eligibility without creating drafts, reserving a lead, or sending. Includes pause, opt-out and prior-reservation reasons. Eligibility is a snapshot; preparation and approval recheck it. No browser or LLM.

Inputs: account (required), lead_id (required), campaign_id (required). Returns: result

process_queueA

Drain queued actions with jittered pacing and daily caps. THIS CALL IS THE APPROVAL GATE for queued work: items execute through the same pacing/dedup/metrics path as every other write action. With account omitted, every account with due items drains (each bounded by max_actions and its own daily caps).

Inputs: account, max_actions. Returns: result

queue_engagementA

Queue a like, retweet, or reply for paced execution. action is one of like/retweet/reply. reply requires text ("auto" scrapes the tweet and generates the reply NOW, so the stored payload is final). Nothing executes until process_queue is called.

Inputs: action (required), account (required), tweet_url (required), text. Returns: result

queue_postA

Schedule a post for paced execution. Pass text verbatim, or a topic to generate the text NOW with the configured LLM (the stored payload is final, list_queue shows exactly what will be posted). not_before is an optional ISO 8601 timestamp. Nothing executes until process_queue is called (or auto_drain, if enabled).

Inputs: account (required), text, media, topic, +2 more. Returns: result

reject_draftA
Idempotent

Reject a pending draft so it can never be approved. Local status change only, nothing touches X.

Inputs: draft_id (required). Returns: result

remove_accountA
DestructiveIdempotent

Remove an account from config/accounts.json. Requires confirm=true. Closes the account's warm session. The backup written during the mutation (config/backups/) is the recovery path; the cookie file is left on disk.

Inputs: account (required), confirm. Returns: result

remove_bookmarkB

Prepare removal of one bookmark. Always requires approve_draft.

Inputs: account (required), tweet_url (required). Returns: object

remove_proxyA
DestructiveIdempotent

Remove a proxy URL from a pool. Requires confirm=true. The response lists accounts still assigned pool:. Emptying a referenced pool is allowed but reported (those accounts fail closed until reassigned).

Inputs: pool (required), proxy_url (required), confirm. Returns: result

reply_to_tweetA

Reply to a tweet. Pass explicit text, or "auto" to generate the reply with the LLM from the tweet's actual content (a read-only fetch is performed so the draft shows the real reply text). In draft mode (default) nothing is posted until approve_draft(draft_id). media accepts local attachments on the async browser backend. For conversation-wide context, read get_thread before supplying explicit reply text.

Inputs: account (required), tweet_url (required), text, media. Returns: result

research_and_stageA

Search each keyword, keep relevant tweets (keyless heuristic), write a reply per tweet with the server-side LLM (persona-aware), and stage one reply DRAFT per tweet. Nothing is posted, review with list_drafts and approve selectively. Requires the 'llm' block in settings.

Inputs: account (required), keywords (required), max_items. Returns: result

resolve_action_outcomeA
Idempotent

After inspecting X, record succeeded or not_sent for an uncertain action. Repairs associated draft/queue history; queued not_sent work is cancelled and never resent automatically. Incorrect not_sent can cause duplicates.

Inputs: account (required), action_id (required), observed_outcome (required). Returns: object

resume_account_actionsA
Idempotent

After resolving a challenge, probe the signed-in home page and clear the local pause. Does not reset budgets.

Inputs: account (required). Returns: object

run_cycleA

Run the legacy batch automation cycle in the background and return a run handle immediately (progress goes to the logs, this never silent-blocks). account limits the run to one account; pipelines is a comma-separated subset of: competitor_reposts, keyword_replies, keyword_retweets, likes, content_curation, community_engagement (mapped onto the account's ActionConfig enable flags for this run only, config files are never mutated; same names as the CLI's x-use run --pipeline). Draft mode does not apply to batch cycles.

Inputs: account, pipelines. Returns: result

search_conversationsB
Read-only

Search the visible inbox locally; results are partial, not full message-history search.

Inputs: query (required), account (required), limit, folder, +2 more. Returns: object

search_profileA
Read-only

Read recent posts from ONE X profile. profile takes a handle ("@nasa" or "nasa"), a profile URL, or a tweet URL (which resolves to its author). Read-only (draft mode does not apply, nothing is posted), but it reuses the account's browser session. account defaults to the first active configured account. Use this to watch specific people and competitors, and to re-read one of your own published posts for its public counts; use search_tweets for topic and keyword discovery. Profile timelines include pinned posts and reposts, so check user_handle before treating a result as the profile owner's own writing. include_images=true additionally attaches the first photo of up to 5 posts as image content (bounded); the per-post media URLs + alt text are always present.

Inputs: profile (required), limit, account, include_images. Returns: object

search_tweetsA
Read-only

Search recent X posts for a query string. Read-only (draft mode does not apply). Reuses the account's warm browser session. account defaults to the first active configured account. include_images=true additionally attaches the first photo of up to 5 tweets as image content (bounded); the per-tweet media URLs + alt text are always present.

Inputs: keywords (required), limit, account, include_images. Returns: object

send_messageB

Prepare a reviewed DM draft for one handle or conversation. Always requires approve_draft, even when draft_mode is off.

Inputs: text (required), account (required), recipient (required). Returns: object

set_account_activeA
Idempotent

Enable or pause an account without deleting it. Pausing closes its warm browser session.

Inputs: active (required), account (required). Returns: result

set_campaign_statusA
Idempotent

Set local campaign status: draft, ready, paused, completed. Pausing immediately blocks preparation and approval of existing drafts. Resume a paused campaign with ready. completed is terminal.

Inputs: status (required), account (required), campaign_id (required). Returns: result

test_proxyA
Read-only

Probe the effective proxy in an isolated, cookieless browser using the configured backend; visits only an IP-echo endpoint, never X. Explicit proxy_url wins; account assignments inherit the global proxy. Returns validated egress IP, startup/request latency and masked route. Async HTTP(S) authentication is supported; legacy Selenium rejects authenticated proxies. Legacy round_robin probes advance its cursor.

Inputs: account, proxy_url. Returns: result

undo_retweetA

Prepare removal of your repost of one exact post. Always requires approve_draft.

Inputs: account (required), tweet_url (required). Returns: object

unfollow_profileA

Prepare unfollowing one exact X profile. Always requires approve_draft.

Inputs: account (required), profile (required). Returns: object

unlike_tweetA

Prepare removal of your like from one exact post. Always requires approve_draft.

Inputs: account (required), tweet_url (required). Returns: object

unlock_inboxA
Idempotent

Unlock the owner's encrypted inbox once using a server environment variable. PIN never appears in tool arguments, drafts, logs or stored state. Inspect get_account_safety for remaining attempts and reset time; never loop on a rejected PIN or challenge.

Inputs: account (required), pin_env_var. Returns: object

update_accountA
Idempotent

Partially update an account. Only provided fields change (None = leave unchanged); pass an empty string to clear proxy. persona sets the freeform persona text; pass an empty string to clear it. cookie_file re-imports cookies like add_account. The account's warm browser session is closed, so the next action cold-starts on the new config.

Inputs: account (required), proxy, persona, is_active, +5 more. Returns: result

update_lead_statusA
Idempotent

Change a lead's local status. Only new/qualified leads can receive campaign drafts. opted_out permanently suppresses further outreach.

Inputs: status (required), account (required), lead_id (required). Returns: result

upsert_leadA
Idempotent

Add/update one local lead by X handle (unique per account). Omitted fields retain their values; notes stay local and never enter messages. Status: new, qualified, contacted, replied, closed, opted_out. Opt-out suppression is permanent and cannot be removed by upserting.

Inputs: handle (required), account (required), tags, notes, +3 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 82 tools

    Disambiguation2/5

    Several clusters are hard to separate: get_profile/get_profile_posts/get_profile_context/search_profile all read profile content, get_thread/get_conversation/search_conversations overlap on reading context, and post_tweet/generate_and_post/queue_post/prepare_thread/draft_post_variations all produce posts through different paths. Likewise reply_to_tweet vs prepare_reply vs queue_engagement vs engage, and approve_draft vs process_queue vs run_cycle all represent competing write pipelines. Descriptions are verbose and do try to differentiate them, but the agent must read long caveats to pick correctly, so boundaries are not self-evident.

    Naming Consistency4/5

    Nearly everything follows a snake_case verb_noun convention (get_*, list_*, create_*, add_*, remove_*, prepare_*, approve_*, cancel_*), which makes the surface predictable. Minor deviations exist: bare verbs like engage and run_cycle, and noun-leading names like draft_post_variations and research_and_stage.

    Tool Count2/5

    82 tools is far beyond a well-scoped set; the server covers accounts, proxies, drafts, queueing, campaigns, threads, conversations, analytics and safety, so the breadth is real, but many tools are narrow variants (bookmark_tweet vs remove_bookmark, unlike_tweet vs undo_retweet). The count makes discovery and correct selection costly even though each tool is individually documented.

    Completeness4/5

    Coverage is unusually thorough: full account/proxy lifecycle, lead and campaign management, draft/queue/approval flow, thread runs, conversations, bookmarks, analytics and safety recovery. Remaining gaps are minor (e.g. no lead deletion, no campaign creation-vs-edit path beyond status, limited inbox message-history search), and workarounds mostly exist.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides programmatic X (Twitter) engagement via MCP, offering 24 tools for search, timelines, notifications, bookmarks, profiles, and tweet actions through a headless browser.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to fully automate X/Twitter interactions including searching, posting, engaging, and managing multiple accounts without paid API keys.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables Twitter/X marketing automation, including tweet search, account analysis, trending topics, and optional AI-generated tweets and scheduling.
      6
      MIT