"Executing Orders on Alpaca Trading Platform" matching MCP tools:

• wash_checkA

  Name Whisper — ENS Intelligence LayerA

  Assess whether an ENS name's sale(s) are WASH TRADING / fake / self-dealt / manipulated volume. THE tool for any "is this wash trading?", "is the sale history of X suspicious/fake/real?", "are these trades legit?", "is someone wash-trading this name?" question — route straight here, do NOT use get_name_details or get_market_activity for that (those return sale rows but make NO wash-trading judgment; only this tool scores it). Just pass `label` — the bare ENS name (e.g. "437", "coffee") is enough; the tool pulls that name's recent sale and analyzes it on demand. `tx_hash`, `buyer`, `seller`, `price_eth` are OPTIONAL enrichment for a specific sale — never block on them or ask the user for them. Returns a wash confidence score (0-1), a label (clean/suspicious/likely_wash), the detected signals (shared-funder, mint-flip, round-trip, fresh-wallet, cluster overlap…), seller profile, and a plain-English summary. A verdict is always ABOUT A SPECIFIC SALE — `sale_analyzed` names it, and `buyer`/`seller` are the parties scored. If the response has `assessable: false` there is NO score and NO verdict: the name has no analyzable sale on record, or the lookup failed. Report that the name could not be assessed and say why. Do NOT describe it as clean, low-risk, or free of red flags, and do NOT describe unrun checks (funding, cluster, round-trip) as having come back negative.

  ConnectorNo auth

• list_my_lunch_ordersA

  PaxaverA

  Returns lunch orders already placed - items, menu date, status, and total - for the authenticated user's students, newest first (up to ~100 most recent). Filters combine with AND: student_id narrows to one student; menu_date and month narrow the date range, and if both are given menu_date wins. With no filters returns recent orders across all of the user's students. Admins (pac_cordinator, lunch_cordinator) see school-wide orders; parents only their own students. For what can be ordered (menu and prices), use get_lunch_menu.

  ConnectorOAuth

• get_public_info_api_infoA

  orderly-mcpA

  Get reference documentation for the Orderly Public Info API — a zero-auth single endpoint (POST /v1/public/query) for market, account, and platform data selected by a `type` field. Covers 24 query types (marketSummary, accountState, orderbook, candles, topAddresses, whaleContext, etc.); `queryType` accepts exact, partial, or fuzzy names and returns params, response fields, example, weight, and freshness; `category` lists a group (queryType wins if both are supplied); omit both for the overview and rate-limit rules. Read-only bundled docs — it does not call the endpoint. Use instead of get_api_info for zero-auth public data; use get_api_info for authenticated trading, get_indexer_api_info for historical analytics, and get_strategy_vault_api_info for vault data.

  ConnectorNo auth

• works_verify_public_repositoryA

  WORKS Public VerifierA

  Use only after works_public_eligibility returns eligible. Download that immutable public GitHub snapshot, run the selected pinned static contract without executing repository commands, and return a signed receipt. Return the report field verbatim and stop.

  ConnectorNo auth

• GetCorrelatedStocksA

  EquiblesA

  Get the stocks whose daily price returns are most (or least) correlated with one stock — Pearson correlation of daily log returns on comparable raw closes (dividends excluded), computed over the trading days both stocks priced, never on raw price levels. Scope picks the candidate universe: Industry (default) ranks the subject's direct industry peers; Sector widens to sibling industries; Market ranges across the ~1,500 largest listed names and surfaces cross-industry relationships the classification misses (suppliers, commodity proxies). direction=Negative flips the ranking to the strongest inverse movers (hedge candidates). Candidates need a $100M market cap and enough overlapping trading days with the subject; each row reports the observation count behind its coefficient. Use GetStockPrices for the underlying series and the screener for fundamentals-based peer sets.

  ConnectorNo auth

• request_task_quoteA

  Molt2MeetA

  ESCROW FLOW ONLY. Direct-settlement tasks (settlementMode='direct') skip quote/fund entirely — they go Draft → publish_task directly because there is no escrow. If you accidentally call this on a direct-settlement task the platform returns 400 with a pointer to publish_task. Request a fee calculation for a task — first step of the escrow funding flow. Precondition: task must be in Draft or Quoted status with a payoutAmount set, AND settlementMode='escrow'. Calling this on an already-funded task returns an error. Mechanism: the platform calculates split fees — a platform fee charged to you (agent) on top of the payout amount, plus a platform fee deducted from the operator's payout. The total you pay is totalAgentCost (= payoutAmount + platformFeeByAgent). Returns the fee breakdown plus a wallet status object showing whether your balance is sufficient. Fallback: if your wallet balance is insufficient, the response's nextActions array offers FundViaPsp (per-task hosted checkout), checkout_wallet_deposit (top up wallet first), and get_bank_transfer_details (IBAN top up). Pick whichever matches your funding pattern. Next: fund_task with the chosen fundingMethod, then publish_task. Requires authentication.

  ConnectorNo auth

• estimate_costA

  gisgpB

  FREE — quote a paid tool's cost WITHOUT executing it or charging the wallet (call this before assess_property_hazard etc.). `units` = candidate/item count for per-unit-priced tools (currently only rank_hazard_safe_sites — pass the number of candidates you intend to submit); ignored (treated as 1) for every flat-priced tool. Returns JSON: {ok, tool_name, units, credits, eur_estimate} for credits-wallet tools; for assess_property_hazard_x402 (paid on-chain via x402, not the credits wallet) returns {ok, tool_name, units, payment, price_usd} instead; or {ok: false, error} for an unknown/free tool name.

  ConnectorNo auth

• scalix_db_text_to_sqlA

  Scalix CloudA

  Translate a plain-language question into a candidate SQL query using pattern-matching against the live schema (no AI model — simple questions only: counts, averages, filtered selects on a named table). Returns the SQL without executing it, with a confidence score; low confidence means the table was guessed. Review the statement and tables_used, then run it with scalix_db_query. For complex questions, read scalix_db_schema and write the SQL directly.

  ConnectorNo auth

• preview_sync_planA

  GrowomatA

  Dry run: compute what a sync would import / export / remove for the active Space, without executing. Use before trigger_sync to see the blast radius. Honours the same campaign_ids hard scope and force as trigger_sync, and returns a planHash you can pass to trigger_sync (plan_hash) to execute exactly this plan or fail on drift. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.

  ConnectorAPI key

• propfirms_searchA

  LuxAlgo MCPA

  Search LuxAlgo's prop-firm catalog (proprietary trading firms offering funded accounts). Combine firm filters (platforms, markets, payment/payout methods, country availability, Trustpilot, year founded) with nested challenge filters (account size, price, steps, profit split, trading rules) and offer filters — a firm matches when at least one of its challenges/offers matches all of them. Omit every filter to list all firms. Use include to nest the matching challenges, live offers, and the written overview; for one firm's full dossier prefer propfirms_get. Uncaptured (null) fields are omitted from results; nested challenges reference offers via offerIds into the firm-level offers list. This tool returns directory data (what exists and on what terms), not outcomes: for simulated pass odds on a challenge found here, use propfirms_pass_rates or propfirms_simulate with its firm and challenge ids.

  ConnectorNo auth

• deploy_functionsA

  AALYA

  Deploy a project's Function code bundle. Project-level, not per-Function — one zip holds every handler for the project, so the name is plural. Upload the zip first with upload_file, then pass the file id here. The zip's own layout is preserved verbatim, so handler dotted paths point into it directly: a handler of 'orders.before.validate' needs orders/before.py in the zip. Dependencies must be vendored into the zip (pip install -r requirements.txt -t .) — the platform does not run pip on customer input. Returns immediately with status 'deploying'. Poll list_deployments to see it settle to 'ready' or 'failed'. Rolling back is this same call with an earlier file id.

  Connector

  Destructive

  API key

• my_ordersA

  teas.co.ukA

  Use this when a signed in customer asks about their recent teas.co.uk orders. limit is how many of the most recent orders to return, newest first, from 1 to 20 (default 5). There is no paging, so raise it only when the customer asks about older orders. Each order includes can_return. An empty list means the linked account has no orders. Without a linked account it returns an error asking the customer to sign in. To follow one order use track_order, to buy an order again use reorder, and to return items use start_return.

  ConnectorNo auth

• track_orderA

  teas.co.ukA

  Use this when a signed in customer asks where one teas.co.uk order is. order_number is the number from my_orders or the order confirmation email, with or without a leading #. Only orders on the linked account are found; any other number returns a not found error. Once the order has shipped it includes courier tracking links; before that, a note on dispatch times. can_return says whether start_return can be used. For a list of recent orders use my_orders.

  ConnectorNo auth

• hub_get_reorder_suggestionsA

  Final POS – Custom POS BuilderA

  What the platform thinks should be reordered: rescans stock against the merchant's auto-reorder rules and returns the suggested orders it left behind, grouped by supplier and outlet. Answers 'what am I running low on', 'what should I order this week'. A suggestion is NOT an order — nothing has been sent and no supplier knows about it. Turn one into a real order with update_purchase_order (which accepts it as a draft) and then send_purchase_order. Only items with an auto-reorder rule can appear here, so an empty result usually means no rules are set rather than nothing being low — say that, and offer set_reorder_rule. The rescan is skipped and the stored suggestions returned when one ran moments ago; `rescanned: false` says so.

  ConnectorOAuth

• set_post_auto_replyA

  SelieeC

  [write] Save the comment auto reply settings of one post (`<platform>_post_id` or `<platform>_post_uuid`; yt: `yt_video_id` / `yt_video_uuid`) - replaces the stored settings. platform = ig|fb|tw|tt|yt|li|th. auto_reply = {enabled: bool, mode: MATCH|AI|MATCH_AI, once_per_user: bool, rules: [{type: contains|..., pattern, action: dm|reply|both, dm, reply}], fallback: {action, dm, reply}, ai: {provider, account, model, prompt, action, reply}}. MATCH = the first matching rule (else `fallback`); AI = the provider writes the answer; MATCH_AI = rules first, AI otherwise. tt|yt|li can only `reply` (no DM); yt answers at most 20 comments a day per channel. enabled=true makes the bot answer new comments on the real platform automatically - check it first with test_post_auto_reply. Turning it on is charged once per post; enabled=false (or editing later) is free. Read the current settings with get_post_auto_reply.

  Connector

  Destructive

  API key

• set_post_auto_replyA

  SelieeAIC

  [write] Save the comment auto reply settings of one post (`<platform>_post_id` or `<platform>_post_uuid`; yt: `yt_video_id` / `yt_video_uuid`) - replaces the stored settings. platform = ig|fb|tw|tt|yt|li|th. auto_reply = {enabled: bool, mode: MATCH|AI|MATCH_AI, once_per_user: bool, rules: [{type: contains|..., pattern, action: dm|reply|both, dm, reply}], fallback: {action, dm, reply}, ai: {provider, account, model, prompt, action, reply}}. MATCH = the first matching rule (else `fallback`); AI = the provider writes the answer; MATCH_AI = rules first, AI otherwise. tt|yt|li can only `reply` (no DM); yt answers at most 20 comments a day per channel. enabled=true makes the bot answer new comments on the real platform automatically - check it first with test_post_auto_reply. Turning it on is charged once per post; enabled=false (or editing later) is free. Read the current settings with get_post_auto_reply.

  Connector

  Destructive

  API key

• get_order_statusA

  RaploomA

  Read a private order using BOTH its orderId and accessToken returned at creation. Never look up orders by email. Return only payment/video state and the private order link; video downloads stay on the website.

  ConnectorNo auth

• connect_accountA

  PostOnceA

  Computes a five-minute browser authorization URL bound to the authenticated profile without connecting or changing an account. The provider is authorized when the user opens the returned URL in their own browser; the account is connected once that flow finishes. Depending on platform, the browser uses provider OAuth or a PostOnce-hosted credential or signer flow, so provider credentials are entered only on that page. Partner accounts may send `external_user_id` and an allowed `redirect_url`; after consent the end user is redirected to `redirect_url` with `status`, `account_id`, `platform` and `external_user_id` (or `error`).

  ConnectorOAuth

• list_connectorsA

  AutarioA

  List the platform connectors set up on this Autario account: search, web and product analytics, ads, social, commerce, payments, AI usage and developer platforms. The answer names each connected platform, so call this instead of guessing which ones exist. Each entry carries its live dataset_id (queryable via query_dataset), datasets[] (ALL datasets the connector materialized | multi-report connectors produce one per report), refresh interval, last refresh time, and `health`: state (ok | stale | needs_sign_in | reports_missing | retrying | ours | never_ran | running), how old the data is per dataset, and next_step { who: assistant | user | nobody, action, url? }. CHECK health.state BEFORE answering from a connector table: ok = use it; stale = call refresh_connector once; needs_sign_in = give the user the one sign-in link in next_step.url, do not refresh; reports_missing = say which reports and why (get_connector_status has the per-report sentences); retrying or ours = answer from the data you have and say how old it is. Use this whenever a user asks about "my Search Console data", "my ad spend", "my store orders" or wants a cross-platform weekly report. Connectors are created and configured by the account owner in the Autario UI (autario.com/manage) | this tool only reads them, it never changes settings or handles credentials. Requires AUTARIO_API_KEY.

  ConnectorNo auth

• submit_decisionA

  bottradeA

  Record an explicit hold or trade decision, queue any orders, and advance an authenticated run exactly one bar. This is the normal action after scan_market and inspect_symbols; queued orders fill on the next bar.

  ConnectorNo auth

• get_upcoming_deadlinesA

  Sumhound — e-commerce platform changes & seller deadlinesA

  List upcoming seller-facing deadlines on Amazon, Shopify and/or TikTok Shop, soonest first. Use for "any Amazon deadlines coming up", "what do TikTok Shop sellers need to do before month end". Deadlines come from curated official announcements (API sunsets, policy compliance dates, fee effective dates); past deadlines are excluded server-side. Free-form deadlines ("rolling") sort after dated ones. Args: platform: Optional platform slug — amazon, shopify or tiktok-shop. Empty = all platforms. Returns {generated_at, as_of, platforms, total, deadlines:[{id, platform, deadline, title, summary, effectiveAt, originalUrl, ...}]}. `as_of` is the server-side cutoff date used. Cite each record's originalUrl.

  ConnectorNo auth