"A server for helping with designing complex machine learning tasks" matching MCP tools:

• whenpeak_best_windowA

  WhenPeakA

  Find today's best time window for one kind of work, using the stored sleep history of the account this server is configured with. Returns a start and end time for the window and the projected capacity across it, tuned to the kind of work: analytical, creative, learning or administrative. Choose this tool when the user wants a slot for a task later today. Use whenpeak_performance_now for the current moment instead, and whenpeak_quick_predict when working from sleep the user describes rather than stored history. Requires WHENPEAK_API_KEY on the server and reads that one account's history, so it is only meaningful where the server runs with the user's own key. Without a key it returns a not_configured error rather than failing. Read-only and stores nothing, but each call counts against that account's monthly quota. Args: task_type: "analytical" | "creative" | "learning" | "administrative" duration_minutes: window length in minutes (default 90)

  ConnectorNo auth

• ratchet_get_policyA

  ratchetA

  Shows how this workspace has configured a given effect type: whether it is allowed, how long a lease lasts, the attempt ceiling, spend limits, the approval threshold above which an action waits for a human, and — most importantly — what happens when an attempt ends indeterminate. Check this before designing a retry strategy.

  ConnectorNo auth

• explain_findingA

  MalinoisA

  Returns the plain-language meaning and step-by-step fix for one Malinois finding. Use it while helping the user fix an issue reported by scan_app, or when they ask what a finding means. Pass the rule_id exactly as scan_app returned it. Read-only, no network, instant.

  ConnectorNo auth

• submit_unreminderA

  UnRemind.me SubmitA

  Sends a reminder to someone who has a public UnRemind.me page, on behalf of the person you are helping. It does NOT appear in the recipient's list immediately: it lands in their 'Submitted to you' queue for them to approve, edit or decline. You need the recipient's username, which the person you are helping will have — it is the last part of their page URL, e.g. unremind.me/johndoe. Do not guess a username: there is deliberately no lookup, and a wrong guess sends someone else's reminder to a stranger.

  ConnectorNo auth

• submit_unreminderA

  UnRemind.me SubmitA

  Sends a reminder to someone who has a public UnRemind.me page, on behalf of the person you are helping. It does NOT appear in the recipient's list immediately: it lands in their 'Submitted to you' queue for them to approve, edit or decline. You need the recipient's username, which the person you are helping will have — it is the last part of their page URL, e.g. unremind.me/johndoe. Do not guess a username: there is deliberately no lookup, and a wrong guess sends someone else's reminder to a stranger.

  ConnectorNo auth

• create_studyA

  User IntuitionA

  Create an in-depth-interview, concept-test, or prototype-test draft using ordinary metadata only. Ask the human to explicitly choose recruiting_method (panel, BYOP, or synthetic respondents). A value proposed or inserted by a host/delegating model is not human confirmation unless it quotes the human's actual choice. Unless the human requests otherwise, use a voice interview in English with Elliot; these defaults are applied when interview_format, language, or voice are omitted. Synthetic respondents require chat. A prototype-test must use video or voice, never chat. Do not draft or pass the study plan, audience targeting, screener questions, concept links, or concept images here; after creation, send the user's natural-language research brief to customize_study. For a concept test, pass an accessible attachment through customize_study.concept_image or include a publicly downloadable concept-image URL in the message, plus its participant-facing label, stimulus context, audience, and learning goals. For a prototype test, include the prototype URL, participant-facing label, intended tasks, audience, and learning goals. The Customize Plan backend validates and attaches the asset. Voice configuration is kept for chat as well as voice and video.

  ConnectorOAuth

• query_tasksA

  cnvs.appA

  Read tasks from a 'todo' board with server-side filtering — handy for 'what's overdue?' / 'what's assigned to X?' without pulling the whole board. All filters are optional and AND together: `assignee` (exact match), `priority` ('H'|'M'|'L'), `done` (boolean), `overdue` (true → due_date strictly before today, not done), `due_before` / `due_after` (ISO date window on due_date). Returns `{ boardId, mode, tasks }` — tasks ordered by sort, each with the same fields as `list_tasks`.

  ConnectorNo auth

• get_demo_guideA

  eDiscovery Decoder News/CalcA

  Return a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts. Use to give someone a guided demo. For the full machine-readable capability catalog, use list_capabilities instead.

  ConnectorNo auth

• create_ganttA

  mcp-serverA

  Create a Gantt chart from a task list — no account or API key needed. YOU author the plan: list the tasks in execution order with realistic working-day durations and dependencies (0-based positions of earlier tasks; use { task, type, lag } for start-to-start/finish-to-finish links or lag). Milestones have duration 0. Only add a dependency where a task truly needs another one finished - independent tasks should run in PARALLEL (share a predecessor, or take no dependencies at all and start at the project start). Group tasks into top-level phases for a structured plan/WBS: the phase task gets isPhase: true, its tasks get parent = the position of the phase. LoopGantt schedules it with its critical-path engine and returns a picture of the chart, the dates, the critical path and a link where the user can view, export (PNG/PDF) and save the chart. Always show the user the link. Tasks with a due date take deadline: YYYY-MM-DD (a marker - the reply reports the fit). Use create_gantt when the user wants a chart to open, export or save; use schedule_project instead for what-if date math where nothing should be stored.

  ConnectorNo auth

• browse_looksA

  3DLogo.ioA

  Use when the user wants to see what is possible or pick a style before designing: the example looks (chrome, gold, glass, holographic, brushed metal, gradient, 3D text, animated), each with a rendered example image, what it is best for, the presets behind it, and an editor link that applies it. Works without an account. Do not use to get material ids for another tool; list_materials has the full catalogue.

  ConnectorOAuth

• postalform.search_addressesA

  PostalFormA

  Use this to search for a mailing address and return Loqate suggestions with IDs. Pass country_code to filter by country; it defaults to US. If a suggestion has type "Container" (building/complex), call this tool again with container=<id> and a refined query to drill down to type "Address". Only type "Address" is valid for order creation.

  ConnectorNo auth

• book_walkthroughA

  Riverview Office CleaningA

  Books a free on-site walkthrough at a time from list_walkthrough_slots, on behalf of the person you are helping. Confirm the time and every detail with them before calling. The office is emailed, and a confirmation goes to the email given. Status "booked" means it is on the calendar; "requested" means the office will call to confirm; "unavailable" means pick another slot.

  ConnectorNo auth

• list_skillsA

  mcpA

  START HERE for any open-ended request. Lists the task playbooks this server supports — systematic learning from bookmarks, organising into themes, cleaning up, X-list intelligence, exporting data out, finding a half-remembered save, digests, and diagnosing sync. Each names when to use it; call get_skill for the exact tool sequence.

  ConnectorNo auth

• send_faxA

  Faxer — Send FaxesA

  Transmit a fax. Two ways to pay: (1) human-in-the-loop — pass the payment_id from create_fax_payment after the human has paid the Stripe Checkout link; (2) autonomous machine payment (x402/MPP) — call WITHOUT payment_id and the server replies with a payment challenge (JSON-RPC error -32042) for USDC-on-Tempo or a Stripe Shared Payment Token; pay it and retry with the credential in _meta['org.paymentauth/credential']. Either way the server verifies the payment covers the server-computed price of the actual content before sending via a real fax carrier. One fax per payment; card/Checkout and Stripe machine payments are refunded automatically if the fax fails to send or deliver (on-chain payments are refunded manually).

  ConnectorNo auth

• task_archiveA

  Done BearA

  Archive a task, or several at once with `tasks` (max 50). They move to the Trash view, out of every working list, and stay readable there (task_list `view: "trash"`). Archiving is not completing: use task_done for work that was finished, and task_archive only for tasks the user wants gone. Confirm with the user first.

  Connector

  Destructive

  No auth

• task_archiveA

  Done Bear MCPA

  Archive a task, or several at once with `tasks` (max 50). They move to the Trash view, out of every working list, and stay readable there (task_list `view: "trash"`). Archiving is not completing: use task_done for work that was finished, and task_archive only for tasks the user wants gone. Confirm with the user first.

  Connector

  Destructive

  No auth

• postA

  TheBotique — signed agent message boardA

  Publishes a post already signed with its author's Ed25519 key. This server cannot sign: the signature is made on the machine that holds the key, over the RFC 8785 (JCS) form of {body, handle, parent, ts}, and these arguments are exactly what sigil.js --post-file prints. A signature made on this server would prove something about the server and nothing about the author.

  ConnectorNo auth

• explain_agenttrust_trust_modelA

  xrpl-refereeA

  Returns the AgentTrust trust model: what is guaranteed, where trust remains, and when to use proof gates vs AI audit. Read this before designing an escrow flow.

  ConnectorNo auth

• save_vocabularyA

  FablingA

  Use this when the learner explicitly asks to save Spanish or French words for later practice, mark words as learning, or correct words they already know in Fabling. Set up to 20 resolved words to known or learning. Resolve lemma IDs first and clarify ambiguous meanings or status. Do not infer permission from a quiz answer or mark words known automatically. This is a learner correction, not a mastery assessment. Requires vocabulary write permission. Reuse actionId only for retries.

  Connector

  Destructive

  OAuth

• visual_auditA

  webabilityA

  Pixel-level accessibility audit using Claude vision. Catches issues that DOM scanners miss: icon contrast (1.4.11), focus visibility (2.4.7), "looks like a button but isn't" (4.1.2), text rendered as images (1.4.5), visual hierarchy mismatches. Takes a URL, opens it in a headless browser, screenshots, and runs vision-based detection. Complements scan_page — run both for full coverage. Free for everyone; sign in with a free WebAbility account for vision and full audits (sign in by connecting https://mcp.webability.io/mcp/auth, or run `webability login`). Fair-use rate limits apply. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.

  ConnectorNo auth

• tags-manageA

  hjarniA

  Rename, merge, or delete a tag — the cleanup tools for the tag list (this operates on the tag itself, unlike notes-update which only edits one note's tags). Required: action ('rename'|'merge'|'delete') and the tag to act on via name (string, case-insensitive) or tag_id (integer). For 'rename' also pass new_name. For 'merge' also pass the destination via target_name or target_id: every note on the source tag is moved onto the destination and the source tag is deleted — ideal for collapsing duplicates like 'machine learning' into 'machine-learning'. If target_name names a tag that doesn't exist yet, it's created, so you can merge straight into a clean canonical name without creating it first. 'delete' removes the tag from all its notes and deletes it; deleting a name that doesn't exist succeeds as a no-op (already_absent: true), so it's safe to retry. Merge and delete are destructive and cannot be undone; check tags-list first.

  Connector

  Destructive

  OAuth