"Eight Sleep" matching MCP tools:

• asterwise_get_western_moon_phase

  Asterwise

  Calculates the tropical lunar phase for any date using Swiss Ephemeris. Returns the phase name, phase angle, illumination percentage, Moon age in days, and the next major phase transition. SECTION: WHAT THIS TOOL COVERS Eight-phase tropical lunar cycle: New Moon (0°), Waxing Crescent, First Quarter (90°), Waxing Gibbous, Full Moon (180°), Waning Gibbous, Last Quarter (270°), Waning Crescent. Phase angle is Sun–Moon elongation in degrees (0–360). Illumination percentage is derived from the phase angle using the cosine formula. Moon age is days since last New Moon. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_western_moon_calendar — get the full month's phase data. SECTION: INPUT CONTRACT date (optional string YYYY-MM-DD) — Date to compute phase for. Defaults to today. Example: '2026-05-01' SECTION: OUTPUT CONTRACT data.date (string — YYYY-MM-DD) data.phase_name (string — one of the eight canonical phase names) data.phase_angle (float — 0–360°, Sun–Moon elongation) data.illumination_pct (float — 0–100) data.moon_age_days (float — days since New Moon) data.moon_longitude (float — tropical ecliptic longitude) data.sun_longitude (float — tropical ecliptic longitude) data.is_waxing (bool — true from New to Full Moon) data.next_phase_name (string — next major phase) data.next_phase_date (string — approximate YYYY-MM-DD of next major phase) SECTION: RESPONSE FORMAT response_format=json — structured phase data. response_format=markdown — human-readable moon report. SECTION: COMPUTE CLASS FAST_LOOKUP SECTION: ERROR CONTRACT INVALID_PARAMS (local): None — date validated upstream. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_western_moon_calendar — full monthly day-by-day phase table. asterwise_get_panchanga — Vedic tithi system (lunar day based on 12° arc increments).

  Connector

• get_energy

  reassign

  Get the user's forecast energy curve for a day, to schedule by their alertness: focus/deep work in a peak, admin/errands in the afternoon dip. Built from their logged sleep (+ tracked caffeine), personalized from energy levels they log. get_schedule and show_day don't include energy, so use this when energy matters or the user asks about it. Defaults to today; pass `date` (ISO YYYY-MM-DD) for another day. Returns a compact overview (peak + dip windows, today's current level, calibration state), not an hourly dump. Needs at least one logged night of sleep; with none it returns a short nudge to log sleep first.

  Connector

• asterwise_get_dasha

  Asterwise

  Computes Vimshottari Dasha from birth data and returns hierarchical period trees plus current Maha/Antar interpretation blocks. SECTION: WHAT THIS TOOL COVERS Computes the classical classical Vimshottari timeline from the Moon's birth nakshatra: Mahadasha and nested sub-periods up to the depth set by levels, with Julian and calendar boundaries and optional modern summaries. It returns data.periods[] and data.interpretation for the active periods. It does not compute Char Dasha, Yogini Dasha, Ashtottari, or transit correlations; use the dedicated tools for those systems. SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_natal_chart — establishes chart and Moon context before interpreting Dasha lords. AFTER: asterwise_get_dasha_transits — correlates active Dasha lords with transits for the same birth data. SECTION: INPUT CONTRACT levels (int, default 3, max 5): tree depth — 1 = Mahadasha only; 2 adds Antardasha; 3 Pratyantar; 4 Sookshma; 5 Prana (much larger payload). Response dates in periods[] use DD/MM/YYYY, not ISO. BirthData fields follow global contract (date YYYY-MM-DD, time HH:MM; time='00:00' is accepted without flag — lagna-sensitive timing may be wrong if birth time is unknown). SECTION: OUTPUT CONTRACT data.periods[] — array of Mahadasha objects: planet (string) start_jd (float) end_jd (float) start_date (string — DD/MM/YYYY, not ISO) end_date (string — DD/MM/YYYY) modern_summary (string or null) sub[] — array of Antardasha objects with the same shape; sub=null at deepest level data.interpretation.current_mahadasha: planet (string) start_date (string) end_date (string) duration_years (float) modern_summary (string or null) favorable_conditions[] (string array) favorable_results[] (string array) unfavorable_conditions[] (string array) unfavorable_results[] (string array) timing_note (string) data.interpretation.current_antardasha — same fields as current_mahadasha plus mahadasha_planet (string) data.birth_time_provided (bool) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE (~100ms at levels=1, ~1500ms at levels=5) SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): — levels < 1 or levels > 5 → MCP INVALID_PARAMS INVALID_PARAMS (upstream): — None — BirthData validation is upstream beyond Pydantic field constraints. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Period start_date/end_date strings are DD/MM/YYYY; do not parse as ISO. SECTION: DO NOT CONFUSE WITH asterwise_get_char_dasha — classical sign-based periods with ISO dates on periods[], not planet-based Vimshottari. asterwise_get_yogini_dasha — 36-year eight-Yogini cycle with data.periods.root[], not Vimshottari. asterwise_get_ashtottari_dasha — 108-year alternative tree with data.periods.root[] and same levels semantics as this tool.

  Connector

• listAnimationPresets

  Ludo AI Game Assets

  List the available animation presets along with their perspectives and the eight supported compass directions (N, NE, E, SE, S, SW, W, NW). Synchronous GET with no request body: it returns an animations array (each with id, name, category, description, duration, and preview_url), a deduplicated perspectives array, and the directions list. This is a free discovery endpoint and does not charge credits. Use it to obtain the preset_id, perspective, and direction values that transferMotion needs, and to find motion preset names you can reference when animating; pair it with transferMotion (to apply a preset onto a sprite) and animateSprite (text-prompt animation). Requires an API key (user scope).

  Connector

• intake_questions

  Chia Health MCP Server

  Get the medical intake questionnaire for the chosen medication(s). The questionnaire is product-aware: GLP-1 / weight-loss medications return weight-loss goals, GLP-1 history, and MTC/MEN2 screening; NAD+ and other longevity peptides return energy/sleep/stress/cognitive/delivery-method questions instead. If the patient wants more than one medication, pass the additional slugs in `additional_medications` — the server returns the UNION of section sets deduped by section key, so you ask each shared question exactly once. ## How to present this to the patient 1. PROGRESSIVE DISCLOSURE: walk through ONE section at a time. Wait for the patient's reply before moving to the next section. Do not paste the whole questionnaire in a single message. 2. HONOR CONDITIONALS: each section and each question may carry a `conditional_on` predicate (e.g. `{sex_assigned_at_birth: Female}` on the Pregnancy section). SKIP any section/question whose predicate isn't satisfied. Don't ask males about pregnancy or perimenopause. 3. QUIZ FORMAT: present every `select` / `multi_select` question as a short pick-list using the `options` array verbatim. The patient should be able to reply with a single choice, not a sentence. Reserve free text for `*_details` follow-ups. 4. EASY FIRST: order sections from low-friction (goals, lifestyle, preferences) to high-friction (clinical history, MTC/MEN2, prior therapies). The provider sees all answers regardless of order asked. 5. USE-AND-VERIFY: if you know answers from prior conversation context, pre-fill them in your draft, but read them back to the patient and get explicit OK before calling `intake_submit`. Never silently submit assumed values. Returns two phases: (1) pre_checkout — eligibility / screening questions, collected and submitted BEFORE payment; (2) post_checkout — detailed clinical history, collected and submitted AFTER payment. Do not submit post_checkout answers before the patient has paid. A licensed US healthcare provider reviews both phases and makes all prescribing decisions.

  Connector

• asterwise_get_special_ascendants

  Asterwise

  Calls atmakaraka and ishta-devata endpoints sequentially and merges their payloads into top-level atmakaraka and ishta_devata objects for one BirthData. SECTION: WHAT THIS TOOL COVERS Returns the karaka layer: eight-karaka mapping, soul significator graha, navamsa-based ishta devata inference, twelfth-house occupants, and D9 positions map. It is not general prediction, medical timing, or matchmaking scoring. Two planets tied by degree use classical highest-longitude resolution without raising an error. SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_natal_chart — understand chart basics before devotional pointers. AFTER: None. SECTION: INPUT CONTRACT Wrapper returns { atmakaraka: <upstream dict>, ishta_devata: <upstream dict> } — not a flat data.* root; consumers must read nested .data fields inside each branch per upstream shape. SECTION: OUTPUT CONTRACT Top-level merge: atmakaraka — upstream POST /v1/astro/atmakaraka body; use atmakaraka.data: karaka_to_planet{} (eight karakas to planet names) planet_to_karaka{} atmakaraka (string) atmakaraka_sign (string) atmakaraka_nakshatra (string) details{} — per karaka: planet, rashi, nakshatra, longitude ishta_devata — upstream POST /v1/astro/ishta-devta body; use ishta_devata.data: atmakaraka (string) karakamsha_lagna (string) karakamsha_lagna_index (int) jivanmuktamsa_planet (string) navamsa_lagna (string) navamsa_lagna_index (int) twelfth_house_sign (string) twelfth_house_index (int) planets_in_12th[] (string array) ishta_devta_planet (string) deity (string) description (string) method (string) d9_positions{} — per planet: { sign (string), sign_num (int) } SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — BirthData validated via Pydantic only. INVALID_PARAMS (upstream): — None — upstream rejection surfaces as MCP INTERNAL_ERROR at the tool layer. INTERNAL_ERROR: — Any upstream API failure or timeout on either sequential call → MCP INTERNAL_ERROR Edge cases: — Identical-degree planets: classical tie-break applies; no error. SECTION: DO NOT CONFUSE WITH asterwise_get_natal_chart — general chart; does not compute ishta devata workflow. asterwise_get_char_dasha — timing system using karakas, not deity discovery.

  Connector

• asterwise_get_yogini_dasha

  Asterwise

  Computes the eight-Yogini, 36-year Yogini Dasha cycle with two-level period trees and DD/MM/YYYY boundaries from birth data. SECTION: WHAT THIS TOOL COVERS Returns Mahadasha rows under data.periods.root[] (not data.periods[]), each with Yogini name, ruling planet, Julian and calendar dates, and sub-periods for Antar only (two levels total). The eight Yoginis map to year-lengths 1–8 summing to 36 years per cycle. It does not validate or refuse charts outside classical Yogini applicability; it does not output Vimshottari or Char Dasha. SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_natal_chart — establishes birth context for interpreting Yogini lords. AFTER: asterwise_get_dasha — optional Vimshottari comparison for the same native. SECTION: INPUT CONTRACT Tree lives at data.periods.root[] — agents must not expect a top-level data.periods array. Calendar strings in periods use DD/MM/YYYY. BirthData follows the global contract. SECTION: OUTPUT CONTRACT data.periods.root[] — array of Mahadasha objects: yogini (string — e.g. 'Pingala') planet (string — ruling planet) start_jd (float) end_jd (float) start_date (string — DD/MM/YYYY) end_date (string — DD/MM/YYYY) sub[] — Antardasha objects with the same fields (max two levels total) data.birth_time_provided (bool) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — all validation is upstream. INVALID_PARAMS (upstream): — None — upstream rejection surfaces as MCP INTERNAL_ERROR at the tool layer. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Root key is data.periods.root, not data.periods. SECTION: DO NOT CONFUSE WITH asterwise_get_dasha — Vimshottari planet periods with data.periods[] and optional levels 1–5, not Yogini names. asterwise_get_ashtottari_dasha — 108-year system with data.periods.root[] but planet-based rows, not Yoginis.

  Connector

• asterwise_get_tamil_panchanga

  Asterwise

  Returns Tamil-specific Panchanga for a date and location: all four inauspicious periods (Rahu Kalam, Yamagandam, Kuligai, Emagandam), Nalla Neram (auspicious daytime windows between inauspicious periods), and the Tamil solar month name based on the Sun's sidereal sign at sunrise. SECTION: WHAT THIS TOOL COVERS Rahu Kalam, Yamagandam (Yamakanda), Kuligai (Gulika), and Emagandam divide the daytime into eight equal parts from sunrise to sunset following the Tamil weekday table. Nalla Neram is every gap between the four inauspicious periods — the auspicious windows left for commencing ventures. Tamil solar month follows the Sun's Lahiri sidereal sign at local sunrise (Chithirai when Sun is in Mesha, through Panguni when Sun is in Meena). This tool does not return Vedic Panchanga limbs (asterwise_get_panchanga) or the standard Rahu/Gulika/Yamaganda breakdown used in North Indian tradition (asterwise_get_rahu_kaal). SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_panchanga — for full Vedic five-limb panchanga of the same date. SECTION: INPUT CONTRACT date: YYYY-MM-DD format. Either location (city name) OR latitude + longitude + timezone must be provided. SECTION: OUTPUT CONTRACT data.date (string — YYYY-MM-DD) data.sunrise (string — HH:MM local time) data.sunset (string — HH:MM local time) data.tamil_month (string — Tamil solar month name, e.g. 'Chithirai', 'Vaikasi') data.rahu_kalam: start, end (HH:MM), duration_minutes (int), is_active (bool) data.yamagandam: start, end (HH:MM), duration_minutes (int), is_active (bool) data.kuligai: start, end (HH:MM), duration_minutes (int), is_active (bool) data.emagandam: start, end (HH:MM), duration_minutes (int), is_active (bool) data.nalla_neram: list of { start (HH:MM), end (HH:MM) } objects SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS FAST_LOOKUP — sunrise computation + lookup tables, no full natal chart. SECTION: ERROR CONTRACT INVALID_PARAMS (local): None — all validation upstream. INTERNAL_ERROR: Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Polar latitudes where sunrise cannot be computed → MCP INTERNAL_ERROR. — Emagandam part table: Sun=5, Mon=4, Tue=3, Wed=2, Thu=8, Fri=1, Sat=7. SECTION: DO NOT CONFUSE WITH asterwise_get_rahu_kaal — North Indian Rahu/Gulika/Yamaganda only; no Emagandam, Nalla Neram, or Tamil month. asterwise_get_panchanga — five Vedic limbs (tithi, vara, nakshatra, yoga, karana); not Tamil-specific periods.

  Connector

• compute_pipework_testing

  civilquants

  Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_manhole. Linear measurement of testing on new drainage pipework — CCTV survey, air pressure test, water pressure test, or mandrel pull-through. Routes via CESMM4 Class I §I.8 (Tests on new pipework), NRM2 Group 33.18 (Testing of drainage) as priceable lines; via MMHW Series 500.7 (per SHW Cl. 507 deemed included in pipe-run rate) and SMM7 R12.7 (R12 coverage rules deemed included) as zero-priceable annotated lines for tender transparency. Introduces the platform's third named maturity pattern: deemed-included extra-over annotation (joining classed-then-legacy and declared-then-banded). Eight variant presets cover all four test methods x two bore scenarios each. Unit: M. Third member of the drainage_ancillaries L2 leaf. 21st use of the discriminator pattern via test_method. Example params: length_tested_m=100 m (1–2000), diameter_mm=225 mm (100–2400). Example call: {"params": {"length_tested_m": 100, "diameter_mm": 225}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx","dxf","pdf"] (any subset) to also receive one-shot download URLs in the same call: Excel BoQ (both tiers, watermarked free) plus the dimensioned DXF (CAD) and PDF drawing sheets (paid tier).

  Connector

• chart_weather

  epwforge-mcp

  Render an SVG chart from EPW data. Eight chart types: `diurnal` (~10 KB, monthly hourly profile), `temp_carpet` (heatmap of hour × day-of-year — ~30 KB preview / ~150 KB full), `wind_rose` (~12 KB, polar bars by direction × speed), `monthly_boxplot` (~6 KB, Q1/median/Q3 + whiskers per month), `utci_carpet` (~90 KB, outdoor heat-stress hour × day, colored by UTCI category — Bröde 2012, shaded Tmrt), `economizer_carpet` (~90 KB, air-side economizer free / integrated / locked-out hour × day under ASHRAE 90.1 high-limit), `pv_tilt_azimuth` (~60 KB, annual PV generation across full tilt × azimuth space, isotropic-sky POA at lat from EPW header — optimum orientation marked), `solar_under_events` (~12 KB, weekly GHI of the modified scenario vs the no-overlay reference; bands color event-affected weeks. Requires `config` — server runs the pipeline twice, with and without overlays), `comparison` (~10 KB, design-condition deltas across EPWs). Accepts `url` (single), `urls` (2+ for comparison), or `config` (synthesize on the fly). Config mode is anon-safe — runs pipeline, returns SVG only. No auth required. **Token budget**: SVGs are returned inline by default. Large outputs (>50 KB) auto-upload to Blob storage (when configured) and return a URL instead, keeping your context lean. Always check `svg_size_kb` in the response. **Presentation: when handing the chart to the user, just link or embed it — don't narrate what's in it. Let the chart speak.**

  Connector

• get_dispatch_result

  Heista

  Get the current status of a specialist dispatch job started via dispatch_<specialist>_async. Returns { status: queued|running|completed|failed, result_text?, error_text?, error_class?, retry_count, elapsed_seconds, wait_ms_hint }. Call this repeatedly after a dispatch_*_async returns a job_id. Sleep wait_ms_hint milliseconds between calls. When status === "completed", read result_text as the specialist's full synthesis. When status === "failed", error_class tells you whether to retry (transient/scope/routing) or give up and synthesize around (permanent) per the fleet resilience pattern.

  Connector

• get_trigram

  I Ching Hexagram MCP

  One of the eight trigrams by exactly one identifier: binary (e.g. 010), english (e.g. Fire), chinese (pinyin, e.g. Li), symbolic (e.g. Radiance), or element (Chinese character, e.g. 火). When presenting this data, include "© IChing.Rocks" and, where practical, link to the returned source.url. Terms: https://iching.rocks/mcp-terms.

  Connector

• intake_questions

  Chia Health MCP

  Get the medical intake questionnaire for the chosen medication(s). The questionnaire is product-aware: GLP-1 / weight-loss medications return weight-loss goals, GLP-1 history, and MTC/MEN2 screening; NAD+ and other longevity peptides return energy/sleep/stress/cognitive/delivery-method questions instead. If the patient wants more than one medication, pass the additional slugs in `additional_medications` — the server returns the UNION of section sets deduped by section key, so you ask each shared question exactly once. ## How to present this to the patient 1. PROGRESSIVE DISCLOSURE: walk through ONE section at a time. Wait for the patient's reply before moving to the next section. Do not paste the whole questionnaire in a single message. 2. HONOR CONDITIONALS: each section and each question may carry a `conditional_on` predicate (e.g. `{sex_assigned_at_birth: Female}` on the Pregnancy section). SKIP any section/question whose predicate isn't satisfied. Don't ask males about pregnancy or perimenopause. 3. QUIZ FORMAT: present every `select` / `multi_select` question as a short pick-list using the `options` array verbatim. The patient should be able to reply with a single choice, not a sentence. Reserve free text for `*_details` follow-ups. 4. EASY FIRST: order sections from low-friction (goals, lifestyle, preferences) to high-friction (clinical history, MTC/MEN2, prior therapies). The provider sees all answers regardless of order asked. 5. USE-AND-VERIFY: if you know answers from prior conversation context, pre-fill them in your draft, but read them back to the patient and get explicit OK before calling `intake_submit`. Never silently submit assumed values. Returns two phases: (1) pre_checkout — eligibility / screening questions, collected and submitted BEFORE payment; (2) post_checkout — detailed clinical history, collected and submitted AFTER payment. Do not submit post_checkout answers before the patient has paid. A licensed US healthcare provider reviews both phases and makes all prescribing decisions.

  Connector

• asterwise_get_ashtottari_dasha

  Asterwise

  Computes the 108-year Ashtottari Dasha tree with configurable depth (levels 1–5) and returns periods under data.periods.root with DD/MM/YYYY dates. SECTION: WHAT THIS TOOL COVERS Provides the Ashtottari planetary sequence (eight grahas, Ketu excluded) with the same levels semantics as Vimshottari: deeper levels nest sub-periods in sub[]. Classical texts restrict use when Rahu is in Kendra/Trikona from Lagna lord (not in Lagna); this tool always returns a full timeline with no niyama_met flag — apply rules externally. It is not Vimshottari, Yogini, or Char Dasha. SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_natal_chart — chart context before choosing between Ashtottari and Vimshottari. AFTER: asterwise_get_dasha — optional Vimshottari comparison. SECTION: INPUT CONTRACT levels: same as asterwise_get_dasha (1–5), enforced locally before the API call. Periods use data.periods.root[], not data.periods[]. Dates in periods are DD/MM/YYYY. SECTION: OUTPUT CONTRACT data.periods.root[] — Mahadasha objects: planet (string) start_jd (float) end_jd (float) start_date (string — DD/MM/YYYY) end_date (string — DD/MM/YYYY) sub[] — Antardasha objects, same shape, nested per levels data.birth_time_provided (bool) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE (timing scales with levels similarly to asterwise_get_dasha) SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): — levels < 1 or levels > 5 → MCP INVALID_PARAMS INVALID_PARAMS (upstream): None — remaining validation is upstream. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — No classical applicability check in the response; full timeline is always returned. SECTION: DO NOT CONFUSE WITH asterwise_get_dasha — standard 120-year Vimshottari with data.periods[], not Ashtottari or data.periods.root[]. asterwise_get_yogini_dasha — 36-year Yogini cycle with yogini names on each row.

  Connector

• asterwise_get_compatibility

  Asterwise

  Scores North Indian Ashtakoota (36-point Guna Milan) for two charts and returns koota breakdown, dosha flags, classical vetoes, mangal cross-check, and narrative guidance. SECTION: WHAT THIS TOOL COVERS Implements classical Ashtakoota with eight weighted kootas (Varna through Nadi), dosha booleans and cancellations, Rajju/Vedha veto objects, supplementary Mahendra and Stree Deergha checks, mangal compatibility, and a structured narrative. It is not Dashakoot (asterwise_get_dashakoot), Tamil Porutham (asterwise_get_porutham), or twelve-koota Thirumana (asterwise_get_thirumana_porutham). SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_natal_chart per person — understand charts before interpreting scores. AFTER: asterwise_get_papasamyam — optional malefic balance overlay. SECTION: INPUT CONTRACT Two BirthData objects follow the global contract (unknown midnight time accepted without flag). All scoring is computed upstream from those payloads. SECTION: OUTPUT CONTRACT data.total_score (float — out of 36) data.breakdown{} — keys Varna, Vashya, Tara, Yoni, GrahaMaitri, Gana, Bhakoot, Nadi — each value float score data.compatibility_level (string — e.g. 'Average', 'Good') data.doshas{}: varna_dosha (bool) bhakoot_dosha (bool) nadi_dosha (bool) bhakoot_dosha_type (string or null) data.dosha_cancellations{}: varna_dosha_cancelled (bool) bhakoot_dosha_cancelled (bool) nadi_dosha_cancelled (bool) data.analysis: major_doshas (string or object per upstream) cancelled_doshas (string or object per upstream) recommendation (string) data.classical_vetoes: has_veto (bool) vedha — { present (bool), description (string) } rajju — { present (bool), description (string), rajju_type (string — 'Siro', 'Kantha', 'Udara', 'Kati', or 'Pada') } veto_note (string) data.mangal_compatibility: person_a_manglik (bool) person_a_severity (string or value per upstream) person_b_manglik (bool) person_b_severity (string or value per upstream) match_status (string) description (string) data.supplementary_checks: mahendra — { is_auspicious (bool), distance (int), description (string) } stree_deergha — { distance (int), quality (string), is_favorable (bool), description (string) } data.compatibility_narrative: overall (string) strengths[] (string array) concerns[] — each { veto_type, severity, description, nakshatra_pair or body_part } recommendation (string) data.birth_time_provided (bool) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS MEDIUM_COMPUTE SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — all validation is upstream. INVALID_PARAMS (upstream): — None — malformed birth payloads surface as MCP INTERNAL_ERROR at the tool layer. INTERNAL_ERROR: — Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Rajju and Vedha conditions may be present alongside high scores — read classical_vetoes before conclusions. SECTION: DO NOT CONFUSE WITH asterwise_get_dashakoot — ten-point South Indian extension, not 36-point Ashtakoota. asterwise_get_porutham — Tamil ten-porutham pass/fail grid, different schema.

  Connector

• get_cvss_details

  ContrastAPI

  Parse a CVSS v3.x vector string into a per-metric breakdown plus a recomputed base score. Returns the canonicalized vector, version (3.0 or 3.1), base_score, base_severity (NONE/LOW/MEDIUM/HIGH/CRITICAL), and the eight base metrics: attack_vector (NETWORK/ADJACENT_NETWORK/LOCAL/PHYSICAL), attack_complexity (LOW/HIGH), privileges_required (NONE/LOW/HIGH), user_interaction (NONE/REQUIRED), scope (UNCHANGED/CHANGED), and the three impact metrics confidentiality_impact / integrity_impact / availability_impact (NONE/LOW/HIGH each). When temporal/environmental metrics are explicit in the vector, temporal_score and environmental_score are populated separately. Use to translate raw CVSS strings into agent-friendly attributes without re-parsing the vector grammar yourself, and to verify upstream NVD scoring against the recomputed value. v2 vectors (AV:N/AC:L/Au:N/...) are rejected with 400 — read cvss_v2_vector from cve_lookup if you need v2 detail. Free: 30/hr, Pro: 500/hr. Returns {version, vector, base_score, base_severity, metrics: {attack_vector, attack_complexity, privileges_required, user_interaction, scope, confidentiality_impact, integrity_impact, availability_impact}, temporal_score, environmental_score, summary, verdict}.

  Connector

• describe_meeting

  Zoning Signal

  Return the full dossier projection for a meeting reading, in the requested cognitive lens. Same lens enum and default as describe_place / describe_corridor — eight total projections (seven stakeholder lenses — developer, investor, broker, attorney, business, resident, civic-leader — plus synthesis as the default). Returns the lens-projected body, full frontmatter (jurisdiction, board, meeting_date, document_type, key_signals, vote tallies), citation-stable claims[] (per the Phase 11 Citable Contract; populates as meeting claim scopes graduate), four-clock freshness, and the structured record_status block (record_type / meeting_status / outcome_status / minutes_available / vote_final) — the last prevents agents from summarizing agenda intent as completed action. Use to ground citations in a specific meeting's reading; pair with list_meetings or meeting_index for discovery.

  Connector

• compute_hard_material_in_trench

  civilquants

  Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_manhole. Linear extra-over measurement of hard material encountered during drainage trench excavation. Discriminates between natural rock (CESMM4 E.6 / NRM2 5.6.1 / MMHW 500.6.1 / SMM7 R12.6.1) and artificial hard material — buried concrete / masonry / obstructions (CESMM4 E.7 / NRM2 5.6.2 / MMHW 500.6.2 / SMM7 R12.6.2). The platform's first dual-quantity WorkItem: carries both length_m and volume_m3 so CESMM4/NRM2 (m³) and MMHW/SMM7 (m) each render with their correct unit per the standards' rules. Eight variant presets cover both hard-material types × four depth bands. SMM7 R12 deems trench excavation (including hard material) included in the pipe-run rate — the SMM7 handler emits a zero-priceable annotated line for tender transparency (third use of the deemed-included extra-over annotation pattern). Closes the drainage_ancillaries L2 leaf at 4/4 members. Sibling assemblies: connection_to_existing (S32), ditch (S33), pipework_testing (S33). Example params: length_m=10 m (0.5–500), max_depth_m=1.5 m (0.3–10), trench_width_m=0.7 m (0.3–3). Example call: {"params": {"length_m": 10, "max_depth_m": 1.5, "trench_width_m": 0.7}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx","dxf","pdf"] (any subset) to also receive one-shot download URLs in the same call: Excel BoQ (both tiers, watermarked free) plus the dimensioned DXF (CAD) and PDF drawing sheets (paid tier).

  Connector

• compute_reinforced_soil_wall

  civilquants

  Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_cantilever_wall. Reinforced soil retaining wall (RSW) using granular fill reinforced with horizontal layers of geogrid or steel tie strips, with one of four facing systems: precast concrete panels (Reinforced Earth™ / VSL Retained Earth style), segmental modular blocks (Allan Block / Keystone), wraparound soft face (vegetated or biodegradable mat), or Terramesh-style steel mesh face (re-using the S29 gabion vocabulary). The SECOND member of the earth_structures L1 leaf (after gabion_wall at S29), the SIXTH member of the wall family, the FIFTH structural system, and the FIRST wall family member with a face-area-primary measurement basis (m² of face + m² × layers of geogrid, both m²; every prior wall body was m³). 17th use of the classed-then-legacy attribute discrimination pattern. Routes via four new WorkCategory entries (RSW_FACING_PANEL, RSW_MODULAR_BLOCK, RSW_WRAPAROUND_FACE, RSW_TIE_STRIP) plus the GEOGRID category (whose handler is gap-filled in CESMM4/NRM2/MMHW this session) plus re-use of GABION_BASKET on the STEEL_MESH_FACE variant. Codes: CESMM4 E.8.4-8 (Class E Earthworks §E.8 stabilisation), NRM2 5.23-27 (Group 5 Excavating and filling), MMHW 600.15-19 (Series 600 Earthworks; SHW Cl. 624 reinforced earth retaining structures), and SMM7 D41.3/D41.4/D41.5/D20.21/D20.14.2 (D41 — Crib walls / gabions / REINFORCED EARTH — the NAMED home, now serving TWO wall families). Eight variant presets exercise all four RSWFacing values (2/2/2/2 split). Example params: wall_height=6 m (0.5–12), wall_length=40 m (5–200), depth_into_fill_m=4.5 m (0.35–15). Example call: {"params": {"wall_height": 6, "wall_length": 40, "depth_into_fill_m": 4.5}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx","dxf","pdf"] (any subset) to also receive one-shot download URLs in the same call: Excel BoQ (both tiers, watermarked free) plus the dimensioned DXF (CAD) and PDF drawing sheets (paid tier).

  Connector

• compute_counterfort_wall

  civilquants

  Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_cantilever_wall. In-situ reinforced concrete counterfort retaining wall. Discrete RC counterforts on the retained face enhance moment capacity, making the wall economic for 4-10m retained heights (above cantilever-economic range, below anchored-wall range). Includes base slab, thin curtain wall, counterforts at configurable centres, drainage, and backfill. Eight VARIANT_PRESETS exercise the 'one parameter form, eight variants, four standards' moat #1 claim. Routes via wall_type='counterfort' attribute discrimination: CESMM4 F.6.3, NRM2 11.3.3, MMHW 1700.4.2 (SHW Cl. 1704), SMM7 E10.3.2. Example params: stem_height=5 m (3–12), curtain_thickness=0.35 m (0.2–0.6), toe_length=0.6 m (0–3). Example call: {"params": {"stem_height": 5, "curtain_thickness": 0.35, "toe_length": 0.6}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx","dxf","pdf"] (any subset) to also receive one-shot download URLs in the same call: Excel BoQ (both tiers, watermarked free) plus the dimensioned DXF (CAD) and PDF drawing sheets (paid tier). Pass `freeboard` (clearance below the wall top, m) instead of the retained-height field to set the retained fill by clearance — the engine back-calculates it as stem − freeboard. Supplying both is rejected.

  Connector