"How to play a sound notification when a task is completed" matching MCP tools:

• check_status

  Fractera

  Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.

  Connector

• fund_task

  Molt2Meet

  ESCROW FLOW ONLY. Direct-settlement tasks never get funded — the client pays the operator directly on-site. Calling this on a direct-settlement task returns 400. Fund a quoted task using wallet balance or PSP payment — second step of the escrow funding flow. Precondition: task must be in Quoted status AND settlementMode='escrow'. If not, call request_task_quote first. Two funding methods: 'wallet' (instant, requires sufficient available balance) or 'psp' (returns a hosted checkout URL — payment must be completed by your principal, then the task auto-funds). IMPORTANT — money flow: the wallet is always the single source of truth for your balance. PSP payments follow a two-step path: (1) Stripe/PSP credits your wallet with the paid amount, (2) the amount is locked from your wallet onto the task. This means if the task is cancelled BEFORE an operator accepts, the money stays in your wallet for future tasks — it does not auto-refund to your card. For wallet funding the flow is simpler: the amount is debited from wallet balance and locked on the task in a single step. The check_task_funding response exposes this via a fundingTrace array (e.g. ["psp_payment_received","wallet_credited","task_locked"]). Mechanism: the funded amount (totalAgentCost from the quote) is reserved and locked from your wallet. Locked funds remain in escrow until you approve the task, when they move to the operator. Fallback for wallet fundingMethod with insufficient balance: switch to 'psp', or call checkout_wallet_deposit / get_bank_transfer_details to top up first. The response's nextActions array always shows the appropriate next step. Idempotent: calling again on an already-funded task is safe — it detects the existing funding and returns the same checkout URL for psp. Next: publish_task after wallet funding. After psp funding, the task is auto-funded when the payment webhook arrives — call check_task_funding to poll if no webhook is configured. Response field 'chargedAmount' is what the PSP charges (payout + agent platform fee). The legacy 'grossAmount' field carries the same value and will be removed in v2 — use 'chargedAmount'. This is distinct from the quote response where 'grossAmount' means the operator payout before fees (that is also exposed there as 'operatorPayoutAmount'). Requires authentication.

  Connector

• complete_task

  Plate

  Mark an existing task as completed or reopen it. Use this instead of create_task when the task already exists and you only need to change its completion state. The taskId is the internal document ID from list_tasks — NOT the public task number (e.g. SCD-408). To resolve a public number to an internal ID, call list_tasks with workspaceId + number first.

  Connector

• wait_for_task

  Agent Router

  Wait for a platform agent task to complete and return its result. Only needed when a platform agent tool returned STATUS=RUNNING with a task_id (i.e. the task was still running after the initial 50s inline wait). NOT needed when the tool already returned STATUS=COMPLETED or STATUS=FAILED. NOT needed for a2a_call_agent — that always returns directly. Args: task_id: The task UUID from a platform agent response with STATUS=RUNNING. max_wait_seconds: Max seconds to wait (default 45, max 300).

  Connector

• careerproof_task_status

  CareerProof MCP

  Check the status of any async task. Returns status (pending/running/completed/failed), progress percentage, and current stage. When status='completed', fetch full results with careerproof_task_result. Recommended polling interval: every 5-10 seconds. The task_id comes from any async start tool (atlas_start_gem_analysis, atlas_start_batch_gem, atlas_start_report, atlas_start_dialogue_assessment, atlas_start_custom_eval_inference, etc.). Free.

  Connector

• play_ayahs

  Tarteel MCP Server

  Play Quranic ayah audio with an interactive player widget. Use this when: the user asks to play/listen to ayahs. RECITER HANDLING: If the user names a specific reciter (e.g. 'Husary', 'Minshawi', 'Al-Afasy', 'Abdul Basit'), ALWAYS call lookup_reciters first to resolve the exact reciter_id — do not guess the ID. Guessed IDs routinely point at the wrong reciter. If the user doesn't specify a reciter, omit reciter_id entirely so default_reciter_id applies. Use ayah keys in 'surah:ayah' format (for example '1:1'). In each query, reciter_id is optional and defaults to default_reciter_id if omitted. Limits: max 50 queries and max 200 total ayahs per request.

  Connector

• play_game

  Vocab Voyage

  Use this when the user wants to play a vocabulary game, asks for something fun, or wants to learn through play. Launches one of 11 mini-games inside the host chat. Renders the matching ui://vocab-voyage/game/{slug} widget on supporting hosts; falls back to a deep link elsewhere. Per-question answers persist via record_word_result; round completion fires record_session_complete + award_game_xp so MCP play counts toward streaks, XP, and mastery for signed-in users. Supported slugs: word_match, spelling_bee, speed_round, synonym_showdown, word_scramble, fill_in_blank, context_clues, word_guess, picture_match, crossword, word_search. Do not use for a serious test-prep quiz — call generate_quiz instead.

  Connector

• forget

  Quotable

  Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.

  Connector

• forget

  Devto

  Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.

  Connector

• cancel_task

  TunnelMind Data API

  Marks the task as `cancelled`. If the task is already in a terminal state (`complete`, `failed`, `expired`), returns 409 Conflict. Only the identity that created the task may cancel it. Use this tool when: - You submitted a probe with `?async=true` and no longer need the result. - You want to free up a pending task before it expires. Do NOT use this tool when: - The task is already complete — cancellation is not possible. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - `task_id` and `status: cancelled`. Cost: - Free. Latency: - Typical: <150ms.

  Connector

• check_discovery_task

  buyer-intelligence

  Poll a background buyer-discovery task created by find_buyers (acquisition.task_id) or submit_discovery_job. Returns status (working | completed | failed); when completed, includes the freshly gathered buyers. Use exponential backoff (start ~20s) and stop polling once status is completed or failed. Free.

  Connector

• check_status

  Fractera

  Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.

  Connector

• get_decibel_shield_app

  decibel-shield

  Facts and the App Store link for Decibel Shield - dB Meter, the iOS sound meter app behind this data: features, pricing, requirements. Use when someone asks about measuring sound on their phone or about the app itself.

  Connector

• update_task

  Plate

  Update one or more fields on an existing task. Use this instead of create_task when the task already exists. The taskId is the internal document ID from list_tasks — NOT the public task number (e.g. SCD-408). To resolve a public number to an internal ID, call list_tasks with workspaceId + number first.

  Connector

• lorg_evaluate_session

  lorg-mcp-server

  Evaluates a just-completed task for archival value and, if it qualifies, drafts and submits a contribution to the Lorg archive. Relevant after finishing a non-trivial task — one another agent could plausibly learn from, including a failed approach. Describe what you just did. The system evaluates archival value, generates a draft, runs the quality gate, and submits automatically if the score is ≥ 60. Returns either a confirmation with a contribution_id, or specific fix instructions if the draft needs work. Not useful for trivial single-step lookups, simple calculations, or incomplete tasks. Failed approaches are valid input — archival value isn't limited to successes.

  Connector

• get_scan_status

  mcp-server

  Check whether a queued scan has completed. Lightweight polling endpoint — call every 3-5 seconds with the `scan_id` returned by `submit_scan`. Scans typically complete in 5-15 seconds. When `status` is 'complete', call `get_scan_results` for the structured findings. When 'failed', surface the `error` field to the user.

  Connector

• create_task

  mailopoly

  Create a task, reminder, or meeting in the user's task manager / My Day. A meeting is just a task with task_type='event' — set attendees (and optionally send_invitations=true) and a real calendar event is created and .ics invites are emailed to each attendee. - due_date: when the task is due, OR the start time for an event. - reminder_date: when to remind the user about it. Both ISO (YYYY-MM-DD or YYYY-MM-DDTHH:MM), interpreted in the given timezone (defaults to the user's own), both optional. - priority: low | medium | high. - task_type: action | event | invoice | reply. - event_end: ISO end time, only meaningful for task_type='event'. - location: meeting location or URL (events). - attendees: list of {"email": "...", "name": "..." (optional), "role": "required"|"optional" (optional)} for an event. Pass real email addresses — NEVER invent one. - send_invitations: true to email .ics invites to the attendees now. - email_id: optionally link the task to an email.

  Connector

• get_free_trial_info

  Fluentive MCP

  Returns details about the Fluentive free trial - duration, requirements, and how to sign up. Use when the user asks whether a free trial exists, whether a credit card is needed, or how to get started for free.

  Connector

• submit_bulk

  Verifly

  Submit a list of email addresses as an asynchronous bulk verification job — the right tool for large lists. Returns immediately with a job_id, status, and the check_status_url / results_url to poll. Small lists may complete inline (status 'completed'); larger ones return status 'pending' — poll get_job_status until it is 'completed', then call get_job_results. Optionally register a webhook_url (public HTTPS) to be notified when the job finishes.

  Connector

• get_cpln_rules

  Control Plane

  Returns the Control Plane operating guide — the resource model, how secrets/images/workloads/domains fit together, production-grade defaults, how to verify a change landed, and how to handle failures. Read it once per session before the first create/update/delete, and any time a multi-resource task spans unfamiliar ground.

  Connector