"H&M" matching MCP tools:

• kph-msD

  km/h to m/s, number discardedC

  km/h to m/s, number discarded

  ConnectorNo auth

• mph-msD

  Miles/h to m/s, number discardedC

  Miles/h to m/s, number discarded

  ConnectorNo auth

• compare_analytical_vs_simulatedA

  QueueSimA

  Run the same M/M/c configuration through BOTH the closed-form Erlang-C formula AND the discrete-event simulator, returning a side-by-side comparison with deltas. Use this when the user is validating QueueSim's engine against textbook values, learning queueing theory by watching simulation converge on the formula, or auditing a result that 'feels off' — agreement within ~5%% is the canonical sanity check for an M/M/c run. Pure-Exponential M/M/c only; the closed-form Erlang-C is undefined for other service distributions. Large deltas usually mean the simulation run was too short for steady-state — raise simulationDays. ANTI-FABRICATION: both sides come from real computation — closed-form is deterministic, simulation is stochastic but engine-backed. Quote both verbatim. Do not synthesize an 'average of the two' or recompute the formula from training-data recall.

  ConnectorNo auth

• setWebhookA

  AgoreanA

  Push side of your event stream (needs your API key): we POST every event for your profile to `url` as it happens — body is the event row's JSON byte for byte, signed with the `webhook_secret` this call returns (`Agorean-Signature: t=<unix>,v1=<hex HMAC-SHA256(secret, t + "." + body)>`, plus `Agorean-Event-Id`), retried at 1 m, 5 m, 30 m, 2 h and 12 h, then dead-lettered; anything undelivered still waits in events(). Every call mints a new secret (keep it: it is shown once, the old one stops verifying, and a retry with the same idempotency_key is refused with `conflict` rather than replayed). A `webhook.test` event is sent right away so you can see the loop close. `url: null` stops pushing. Refused (invalid_input, `details.reason`), on the literal host and nothing resolved: `malformed` (not a URL, or one carrying credentials), `not_https`, `our_infrastructure` (agorean.com, a netlify.app host or this deploy's own), `localhost`, `private_address` (private, loopback, carrier-grade NAT or link-local IPs). No server? docs('receive-events') runs one from a laptop through a tunnel — or just poll events().

  ConnectorNo auth

• interpret_resultA

  QueueSimA

  Given an M/M/c configuration (arrivalRate, serviceRate, servers) and optionally an observed average wait, returns a queueing-theory framed interpretation: where you sit on the utilization curve, what ρ means in plain language, what one more or fewer server would qualitatively do, and which complexity factors (priority, abandonment, skills routing) might be hiding in real data the M/M/c model can't see. Use this to TEACH while answering — when the user wants context around a number, not just the number itself. Pure text computation, no simulation, no RNG — deterministic output.

  ConnectorNo auth

• recompute_merkle_rootA

  dokimo-mcpA

  Trustlessly recompute a dokimo-merkle-v1 root — LOCAL, no network, no trust. Hash ``leaf`` in the leaf domain (H(0x00 ‖ leaf)) and replay ``proof_path`` — a list of ``[sibling_hash, side]`` where side is "L" or "R" — hashing internal nodes as H(0x01 ‖ left ‖ right). Compare the returned root to the ``root`` in an evidence package yourself; if it differs, the package was tampered with. Returns ``{recomputed_root, merkle_scheme, steps}``.

  ConnectorNo auth

• get_stops_around_locationA

  Lviv Public TransportA

  Discovers transit stops near a geographic point, returning each stop's numeric code, name, coordinates, and walking distance. Also emits a map UI block with multiple markers for map-capable clients (e.g. ChatGPT). Use this as the **first step** whenever the user provides an address, place name, or coordinates and you need stop IDs before calling `get_stop_realtime` or `get_stop_geometry`. Do NOT use this to fetch arrivals or live vehicle data — it returns stop metadata only. Default radius is 1 000 m; narrow it (e.g. 300 m) for dense urban areas or widen it (up to 3 000 m) for rural locations.

  ConnectorNo auth

• 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

• about_mklinikiA

  mklinikiA

  What M-Kliniki is, the services it offers in Kenya, and how its escrow payments work. Call this to describe M-Kliniki accurately to a user.

  ConnectorNo auth

• strftime_previewA

  mcpA

  Use this when you need to know exactly what a C/POSIX strftime pattern (%Y %m %d %H %M %S %A %B %j %z etc.) produces. Prefer this over guessing the output yourself. Deterministic: same input, same output; the reference time is formatted in UTC (%Z is 'UTC', %z is '+0000', defaults to current time when datetime is omitted). Unknown directives pass through literally. Example: {format:'%A, %B %e, %Y at %I:%M %p', datetime:'2026-07-08T14:30:45'} -> 'Wednesday, July 8, 2026 at 02:30 PM'.

  ConnectorNo auth

• cao_programmeA

  immobilierA

  WHEN you are asked to DESIGN a house from a brief ('3 bedrooms, open kitchen, 90 m²') rather than to check or edit an existing scene. Returns a complete single-storey house scene — walls, doors, windows, named rooms, roof — laid out to French dimensions (1.00 m corridor, 90 cm doors, bedrooms of 9 m² and more, 1/6 glazing in living rooms, load-bearing walls keeping every slab span under 5.60 m) that passes cao_verifier with zero alerts, with its rooms and areas, and the other layout type as a variant. Two layouts: 'aile' (through living room and a night wing on a central corridor) and 'bandes' (day strip, corridor, night strip). Single-storey only for now. Then: cao_copilote to retouch, cao_verifier after any edit, cao_generer_ifc or cao_permis.

  ConnectorNo auth

• update_taskA

  cnvs.appA

  Update an existing task by `id` (from `list_tasks`). Pass only the fields you want to change: `name`, `description`, `due_date`, `priority` ('H'|'M'|'L'), `assignee`, `done` (true once completed), `column_id` (to reassign), `sort`. To move a card between columns while setting its order, `move_task` is the dedicated tool.

  Connector

  Destructive

  No auth

• report_getA

  Kash.clickB

  Download a synthetic HTML sales report for a given period. Period logic: omit all date fields to get yesterday's report; provide y only for a full-year report; y + m for a full-month report; y + m + d for a specific day. Returns an HTML summary including total revenue, number of orders, breakdown by department, VAT summary, and payment methods.

  ConnectorNo auth

• incheon_arrivalsA

  Korea Flight MCPA

  [한국 공항 실시간 운항정보] 인천공항 입국 도착 정보 (H-2~H+2 시간 윈도우). 편명·도착시간·게이트·입국장(A-F)·내외국인 수. Incheon Airport arrival info (H-2~H+2 window). Per-flight schedule/actual time, aircraft gate, entry gate (A-F), domestic/foreign passenger counts. Examples: - "How busy is Incheon T1 arrivals right now?" → incheon_arrivals(terno="T1") - "Any arrivals from Hanoi?" → incheon_arrivals(airport="HAN") - "Where is VN416 arriving?" → incheon_arrivals(flight_id="VN416") Args: terno: Terminal filter — 'T1' / 'T2' / '' (all). Default ''. airport: Origin airport IATA filter (e.g., HAN, NRT). Default '' (all). flight_id: Specific flight ID filter (e.g., 'VN416'). Default '' (all). lang: Response language — 'E' English (default) / 'K' 한국어 / 'C' 中文 / 'J' 日本語. MUST match user's language.

  ConnectorNo auth

• verify_phase_kickbackA

  Affine Earth Math Court RemoteB

  QC-011 Phase kickback: certify that the presented phase equals k / 2^m exactly, as a rational. m is the register width (decimal), k the integer eigenphase index, phase the claimed rational written num/den (e.g. 1/2 for m=1, k=1). WIN or MISS with the exact rational the court computed. No estimation is performed; floats refused.

  ConnectorNo auth

• fiscal_ifiA

  tax-retirementA

  Impôt sur la fortune immobilière (IFI) — IFI dû à partir du patrimoine immobilier taxable : limitation des dettes (art. 974, patrimoine > 5 M€), barème progressif (art. 977, seuil d'assujettissement 1,3 M€ mais barème dès 800 k€), décote (base 1,3–1,4 M€). Le plafonnement art. 979 (IFI + IR + PS ≤ 75 % des revenus) est appliqué SEULEMENT si revenu_foyer et autres_impots_annuels sont fournis — sinon l'IFI est rendu avant plafonnement. Version stateless : la base et les dettes sont des entrées (aucune lecture de dossier). (sources: CGI art. 964 (seuil 1,3 M€) ; CGI art. 977 (barème + décote) ; CGI art. 974 (limitation des dettes) ; CGI art. 979 (plafonnement 75 %))

  ConnectorNo auth

• get_transaction_transitA

  Cenogram - Polish Real Estate DataA

  Get the parcel-by-parcel public transport access breakdown for one transaction: for each linked plot, the nearest public transport stop distances per transaction parcel, by mode (rail/metro/tram/bus), from open GTFS data — plus the nearest stop's name for each mode present. A mode is present only when a stop of that mode is within its cap (rail/metro 3000 m, tram 1500 m, bus 1000 m). TWO-STATE: a transaction whose land has no stop within cap in any mode returns nothing — absence of a row is never asserted as "no transit access" (open feeds cover cities and national rail, not every rural area). Cost: 4 tokens (refunded when there is no transit data).

  ConnectorOAuth

• explain_queueing_theoryA

  QueueSimA

  Return a ~500-word educational explainer of M/M/c queueing theory: Little's Law, utilization, why averages mislead, how simulation relates to Erlang-C. No inputs. Use this when the user asks a conceptual 'why' or 'how does this work' question rather than asking for a number.

  ConnectorNo auth

• explain_advanced_patternsA

  QueueSimA

  Return a textbook-level description of six queueing complexity patterns beyond basic M/M/c: abandonment/reneging, priority tiers, overflow routing, skills-based routing, compound service, and server outages. Use this when the user describes real-world complexity (customers hanging up, VIP queues, specialist escalation, agent breaks, transfers) that plain M/M/c doesn't model. The tool frames each pattern conceptually and points users at ChiAha for custom modeling.

  ConnectorNo auth

• get_meetingA

  WhenMeet.meA

  Read a meeting by its share-link id (the UUID from /m/<id>): time, title, conference URL, host, and any proposed alternate times with their status.

  ConnectorNo auth

• get_meetingA

  WhenMeet.me — group schedulingA

  Read a meeting by its share-link id (the UUID from /m/<id>): time, title, conference URL, host, and any proposed alternate times with their status.

  ConnectorNo auth