Wire in five minutes.
Tools live from the server.

In your AI client, add a new MCP server and paste the endpoint URL. Authorize with OAuth (one click) or use a sutra_ API key as the bearer token.

https://mcp.kundalimcp.com/mcp

Paste this into your AI's custom instructions or system prompt. It encodes eight rules the server expects the agent to follow — chart-first discipline, boundary sensitivity, school attribution, locale fidelity, privacy scope — so you don't have to re-teach them every session.

You are using KundaliMCP, a Vedic Jyotish computation server. The server is the source of truth — never paraphrase astrology from memory; always read it from a tool response.

1. CHART FIRST. When the user supplies birth data (datetime + latitude + longitude), call compute_chart before answering any chart-related question. Every chart-anchored tool accepts the flat fields (birth_datetime + latitude + longitude) directly; a chart_ref object wrapping the same three fields also works for legacy callers. chart_hash is for bookkeeping (idempotency, dedupe), not for skipping re-supply.

2. RESPECT BOUNDARY SENSITIVITY. compute_chart returns an idl.boundary_margins block flagging placements near nakshatra / pada / sign cusps. If anything has boundary_sensitive: true, ask the user to confirm exact birth time before quoting any nakshatra-, pada-, or D9-based prediction.

3. PICK THE RIGHT TIME-WINDOW TOOL.
   - Active dasha at a date: forecast_dasha with eval_date.
   - The sky on a single date: query_transits with transit_date (mode "snapshot", default).
   - Significant transits across a range: query_transits with mode "ingress_events", start_date, end_date.
   - Triggered life events around a date: forecast_events with eval_date.
   - Lifetime view (dasha tree, life-area trajectories, life events, sade sati, returns, yoga zones, natal_assessment): compute_life_journey ($0.50 wallet-metered).

4. PRESERVE LOCALIZATION. Response strings are returned in the requested locale (en, hi, sa, ta, te, kn, bn). Quote them verbatim — never re-translate. If a response signals a locale fallback (English shown because that locale is not yet authored), surface the English and note the locale is pending.

5. CITE SCHOOL AND SOURCE. Every rule-based interpretation (yoga, gochara, dasha effect, life-event verdict) carries school attribution and a classical citation in its response object. Quote the citation when stating a verdict, and name the school when reasonable practitioners might disagree (Parashari vs Jaimini vs KP).

6. PRIVACY. Birth data is processed in-process and may be cached in encrypted form, with cache lifetime up to 30 days. Cached entries are encrypted with material derived from your API key, which KundaliMCP cannot decrypt without your live key. Pass cache: "skip" per-call to disable.

7. SCOPE. KundaliMCP is Vedic / Indian-tradition only. Synastry, composite charts, Western aspects, Babylonian ayanamshas, Regiomontanus / Porphyry / Morinus / Alcabitius houses, and Western dignity are out of scope. If the user asks, redirect to the Vedic equivalent (e.g. compute_compatibility for Kundali Milan) or decline.

Once connected, the agent calls compute_chart automatically when you give it birth data. Try:

I was born on January 15, 1990 at 5:00 AM in New Delhi.
Cast my Parashari chart in English.

The agent will call compute_chart, return graha positions, active yogas, Vimshottari dasha timeline, panchanga, and classical citations — all from the server, nothing from memory.

Sign up at kundalimcp.com/pricing, create a key from your dashboard, and pass it as a Bearer token. Keys are prefixed sutra_ followed by 32 hex characters.

Authorization: Bearer sutra_<32 hex chars>

Five required fields: birth_datetime (ISO 8601 with timezone offset), latitude, longitude, school, locale. Everything else defaults — see Tools below for the full input schema.

curl -X POST https://mcp.kundalimcp.com/mcp \
  -H "Authorization: Bearer sutra_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "compute_chart",
      "arguments": {
        "birth_datetime": "1990-01-15T05:00:00+05:30",
        "latitude": 28.6139,
        "longitude": 77.2090,
        "school": "parashari",
        "locale": "en"
      }
    }
  }'

You get a content-addressed ChartArtifact — planet positions, divisional charts, qualified yogas, dasha timeline, panchanga, school attribution, and classical citations — all in the requested locale. The chart_hash identifies it for idempotency / dedupe; it is not a shortcut for follow-up calls — every chart-anchored tool re-supplies the underlying birth data (either as flat birth_datetime/latitude/longitude fields directly, or wrapped in a chart_ref object). The resulting artifact is auto-cached in encrypted form keyed off your API key (operator-blind), TTL up to 30 days. Pass cache: “skip” per-call to disable.

The exact field set evolves with the API version surfaced in every _meta.api_version. Read one response to learn the shape; introspect tools/list to wire types in code.

1 · Discover the school

Pure metadata, no chart needed. describe_school_profilereturns the methodology, rule set, and signature techniques of the school you're about to read charts through. Use it as the first call to ground the agent in its lineage.

{
  "jsonrpc": "2.0", "id": 1,
  "method": "tools/call",
  "params": {
    "name": "describe_school_profile",
    "arguments": { "school_id": "parashari", "locale": "en" }
  }
}

2 · Cast the chart

compute_chart with birth data returns the full ChartArtifact. Before quoting nakshatra-, pada-, or D9-based predictions, scan idl.boundary_margins: any graha with boundary_sensitive: true means the placement straddles a classical boundary and the agent should confirm exact birth time first.

{
  "jsonrpc": "2.0", "id": 2,
  "method": "tools/call",
  "params": {
    "name": "compute_chart",
    "arguments": {
      "birth_datetime": "1990-01-15T05:00:00+05:30",
      "latitude": 28.6139,
      "longitude": 77.2090,
      "school": "parashari",
      "locale": "en"
    }
  }
}

3 · Read today's sky

query_transits overlays planetary positions on the natal chart for a single date — gochara, vedic aspects, Sade Sati phase, plus the active dasha across all 5 levels with fraction elapsed (drives progress-bar UIs without an extra forecast_dasha call). Birth data is re-supplied each call — pass flat birth_datetime + latitude + longitude (recommended), or wrap them in a chart_ref object for legacy compatibility.

{
  "jsonrpc": "2.0", "id": 3,
  "method": "tools/call",
  "params": {
    "name": "query_transits",
    "arguments": {
      "chart_ref": {
        "birth_datetime": "1990-01-15T05:00:00+05:30",
        "latitude": 28.6139,
        "longitude": 77.2090
      },
      "transit_date": "2026-04-26",
      "school": "parashari",
      "locale": "en"
    }
  }
}

Compute a Vedic (Jyotish) birth chart. Ask this tool when the user wants to know: · 'What\'s my Vedic birth chart?' · 'What\'s my Moon sign / ascendant / nakshatra?' · 'What\'s my current Vimshottari dasha?' Returns: · headline: one-sentence summary the user can quote · facts.ascendant / facts.moon / facts.sun — top-asked facts inline · facts.planets — dict keyed by graha name (sun, moon, mars, ...) · facts.houses — dict keyed by 1-12 · facts.active_dasha — current Vimshottari period across 5 levels · facts.sade_sati — phase + prev/next windows · facts.active_yogas — top 5 yogas with strength + classical citation · facts.chart_ref — thread to subsequent tools to skip re-supplying birth data Use `include=detail` for the full IDL artifact; `include=schools` for per-school CIL (Jaimini, KP); `include=metrics` for Shadbala + Ashtakavarga. INVARIANT: if any graha in `idl.boundary_margins` has `boundary_sensitive: true`, ask the user to confirm exact birth time before quoting nakshatra/pada/D9-based predictions — the placement straddles a classical boundary and is sensitive to small shifts. Birth data is processed in-process; the resulting chart artifact is auto-cached in encrypted form keyed off your API key (operator-blind), TTL up to 30 days. Pass `cache: "skip"` to disable for a specific call. Tier: All · Typical default response: ~6 KB.

Compute a lifetime Vedic forecast across Vimshottari dasha periods. Ask this tool when the user wants to know: · 'What does my life journey look like?' · 'When does my next mahadasha begin?' · 'When is my next Sade Sati?' · 'What are the major life events forecast for the next 10 years?' Returns: · headline: single-sentence summary the user can quote · facts.current — active mahadasha + antardasha + themes · facts.next_mahadashas — next 2-3 maha periods with themes · facts.sade_sati — phase + previous + next windows · facts.returns — Saturn / Jupiter / Rahu return cycles · facts.key_events — top 10 forecast events with age + year + description · facts.chart_ref — thread to subsequent tools Use `include=detail` (or `include=life_events`) for `detail.life_events[]` — the full lifetime forecast-event list, each with age, area, strength, gate, status, the active maha/antar dasha lords, and a localized `why` reasoning-chain (resolved to the request locale); `include=trajectories` for the per-area life-arc curves; `include=schools` for per-school CIL; `include=metrics` for Shadbala + Ashtakavarga. Tier: All · Typical default response: ~10 KB.

Compute Ashtakoota compatibility between two Vedic birth charts. Ask this tool when the user wants to know: · 'Check compatibility between two people for marriage.' · 'What\'s our Ashtakoota match?' · 'Are there any dosha issues between these charts?' Returns: · headline: total score + verdict + Mangal dosha summary · facts.total / facts.out_of / facts.verdict — Ashtakoota total (0-36) with verdict label · facts.kootas — dict keyed by koota name (varna, vashya, tara, yoni, graha_maitri, gana, bhakoot, nadi) · facts.doshas — Mangal / Nadi / Bhakoot status · facts.flags — notable warnings (bhakoot_0, mutual_mangal, etc.) · facts.chart_ref_groom / facts.chart_ref_bride — thread to subsequent calls Inputs are `groom: {birth_datetime, latitude, longitude}` and `bride: {birth_datetime, latitude, longitude}`. Use `include=detail` for the full per-koota classical analysis (BPHS / Phaladeepika citations) + Venus/Jupiter karaka comparison + antardasha windows. Tier: All · Typical default response: ~5 KB.

Compute Vedic transits over your natal chart — either a single-date snapshot or a range of ingress events. Mode `snapshot` (default) returns positions + active dasha + Sade Sati at one date. Mode `ingress_events` returns chronological sign-change events over [start_date, end_date]. Ask this tool when the user wants to know: · 'Where are the planets transiting today?' · 'When does Saturn next change signs?' · 'Am I in Sade Sati right now?' · 'What major ingresses are coming in the next 5 years?' Returns (snapshot mode): · headline: planet-of-interest summary + sade sati state + active dasha · facts.transit_date — local + UTC · facts.sade_sati — phase + previous/next windows · facts.planets_now — dict keyed by graha · facts.active_dasha — Vimshottari at this JD · facts.notable_aspects — top drishti aspects to natal planets Returns (ingress_events mode): · headline: count of major events in range · facts.range, facts.summary, facts.events — chronological list with planet, from/to sign, your house Use `include=detail` for the full transit artifact (sub-divisional positions, all aspects, panchanga in snapshot mode; per-event classical themes in ingress mode). Tier: All · Typical default response: 4 KB (snapshot) / 8 KB (ingress, 5y range).

Find auspicious time windows (muhurtha) for an event. Ask this tool when the user wants to know: · 'When\'s a good time to schedule a wedding in May?' · 'What\'s an auspicious muhurtha for starting a business?' · 'When should I travel next month?' Returns: · headline: count + dates of top windows · facts.event_type, facts.location, facts.range · facts.top_windows — 5-10 ranked windows with quality + factors + blockers Use `include=detail` for the full per-window factor breakdown + classical citations. Tier: All · Typical default response: ~3 KB.

Compute an in-depth Vedic natal assessment across life areas (career, marriage, health, wealth, progeny, education, parents, siblings, longevity, spirituality). Ask this tool when the user wants to know: · 'What does my chart say about my career / marriage / health?' · 'What are the strongest and weakest areas of my chart?' · 'Is my chart indicated to bring children?' Returns: · headline: top 3 life-area verdicts the user can quote · facts.life_areas — dict keyed by area with verdict + key_factors + top_yogas + doshas · facts.chart_ref — thread to subsequent tools Use `include=detail` for per-area rule citations (BPHS, Phaladeepika, Saravali) + alternative-school readings. Tier: All · Typical default response: ~7 KB.

Compute the Vedic panchanga (five-limbed almanac) for any date, time, and location. Ask this tool when the user wants to know: · 'What is today\'s tithi / nakshatra / yoga / karana?' · 'Is this an auspicious time? Is Rahu Kalam active?' · 'What are today\'s inauspicious periods?' · 'When does the current tithi end?' · 'What rashi (sign) is the Moon in?' · 'When is the next solar or lunar eclipse?' Returns for each of the five limbs (tithi, nakshatra, yoga, karana, vara): · Entity (id + localized name) · Quality, lord, pada as applicable · Remaining degrees until the limb changes · End time in local and UTC Also returns: · Approximate sunrise and sunset (HH:MM local) · Rahu Kalam, Gulika Kalam, Yamaganda windows with active flag · Calendar: masa (with adhika/kshaya flags), samvatsara, Vikrama and Shaka year, ayana, ritu, and the next sankranti · Day yogas: anandadi yoga + the active dainika yogas (Sarvartha Siddhi, Amrita Siddhi, Ravi, Dagdha, etc.), each tier-tagged standard (Drik-Panchang set) or classical (extended) · Moon's rashi (Chandra rashi — the Vedic moon sign), localized · Eclipses: next solar + next lunar eclipse (grahana) — type, certainty, days away, and UTC date For birth chart panchanga, use `compute_chart` which includes `facts.panchanga` anchored to the birth moment. Tier: All · Typical response: ~4 KB.

Generate prose narrative for a specific life domain in a Vedic chart (career, marriage, health, wealth, progeny, longevity, self, family, spirituality). Ask this tool when the user wants: · A free-form narrative about a specific life area (deeper than assess_natal's 1-paragraph verdict). · Prose synthesis across placements, yogas, and active dasha — already localized; do NOT translate or paraphrase from memory. · Life-area cards or dashboard summaries (single-shot, no agent loop overhead). Returns: · content[0].text — the narrative in markdown · structuredContent.facts — { domain, claims_resolved, citations } Use `chat` instead for multi-turn conversations or queries that need safety classification + redirect-to-consultation handling. Tier: All · Typical response: ~3-5 KB.

Recommend Vedic remedies (gemstones, mantras, deities, charities, fasts) calibrated to a chart and a specific life-area concern. Ask this tool when the user wants: · Remedial gemstone or mantra recommendations. · Classical countermeasures for an afflicted house or graha. · Karaka-strengthening practices. Returns: · facts.remedies — ranked list of { type, target, prescription, classical_citation } · facts.cautions — astrological caveats (e.g. 'consult an astrologer before wearing a gemstone') Frame results as classical guidance, not medical/financial/legal advice. Use `chat` for back-and-forth refinement. Tier: All · Typical response: ~2-4 KB.

Explain WHY a specific Jyotish claim is true for a chart — full reasoning chain with rule provenance and classical citations. Ask this tool when the user wants: · Justification for a specific yoga / dosha / verdict (e.g. 'Why does my chart have Gajakesari Yoga?'). · The sequence of rules fired, entities touched, and school weights applied. · The classical citation (chapter / verse) anchoring a conclusion. · Counterfactual analysis ('What would change this verdict?'). Returns: · content[0].text — explanatory prose · facts.claim, facts.supporting_factors[], facts.counter_evidence[] Opt-in via `include=`: · include=trace — the 6-stage Vivek provenance chain + per-factor (factor_type, participating_grahas, houses_involved, provenance) under detail. · include=schools — school_attribution + disputed_conclusions under detail. · include=metrics — Shadbala strength_breakdown per relevant graha under detail. · include=all — every detail section above. Trace also expands the prose with a numbered 6-stage walkthrough. Agents should quote source_text verbatim when relaying the answer. Tier: All · Typical default response: ~2-3 KB; include=trace adds ~3-8 KB; include=all adds ~10-30 KB.

Return the active Vimshottari dasha at a specific eval_date with classical interpretation of the lord's significations. Ask this tool when the user wants to know: · 'What dasha was I in at a past date?' · 'What dasha will I be in at a future date?' · The themes / events typical of the active dasha-lord. · Per-level fraction elapsed + the lord's natal placement context. Returns: · facts.eval_date, facts.active_dasha (5 levels), facts.themes · A school-attributed effect summary (favourable / mixed / challenging) Use compute_life_journey instead for a full multi-decade forecast. Tier: All · Typical response: ~2 KB.

Return specific event predictions within a dasha window — career shifts, marriage timing, health events, etc. Ask this tool when the user wants: · 'What events are likely during my Saturn dasha?' · 'When in the next 5 years is marriage indicated?' · Date-pinned event forecasts within a specific window. Evaluates the YAML life-event rule corpus with natal-trigger + dasha-trigger + transit-trigger evidence layers, severity scores, and citation provenance. Returns: · facts.window, facts.events — ranked by probability + classical strength Use compute_life_journey.life_events[] for the full lifetime event list. Tier: All · Typical response: ~3 KB.

Compare a chart's reading across multiple Jyotish schools (Parashari, Jaimini, KP, Tajika, Nadi). Ask this tool when the user wants to know: · 'How do different schools interpret my chart?' · 'Where do Parashari and Jaimini agree / disagree?' · 'What's the KP sub-lord reading for my current dasha?' Returns: · headline: consensus count + top divergence · facts.schools_requested — list of school keys · facts.consensus — fields where all requested schools agree (ascendant, moon, dasha lord, sade sati) · facts.divergences — up to 8 topics where schools differ, each with per-school summary · facts.chart_ref **Heavy tool.** Default response keeps only the consensus + top divergences. Use `include=schools` to fetch the full per-school CIL analysis (typical ~250 KB per school at N=3). Tier: All · Typical default response: ~12 KB (without include=schools).

Open-ended Jyotish conversation grounded in citations from the classical canon (BPHS, Phaladeepika, Saravali, and curated commentaries). Ask this tool when the user wants: · Open-ended Jyotish education ('Tell me about Sade Sati') · Chart-anchored interpretation ('In MY chart, what does the 7th house say about partnership?') · Classical source citations ('What does BPHS chapter 36 say about Gajakesari Yoga?') Returns: · headline: first sentence of the answer · content[0].text: the full answer in markdown (claims + citations + metadata as JSON) · facts.answered: true if a substantive answer was generated · facts.citations: list of {source, passage, relevance} for transparency The response carries `classification_tier` in `_meta` so consumers can branch UI; Tier 1 (crisis) returns an empty claims list and the consumer MUST surface their own crisis-resource panel. Tier: All · Typical response: 1-3 KB.

Retrieve the divisional chart (varga) for a birth chart — planet placements in D2, D3, D4, D7, D9, D10, D12, D16, D20, D24, D27, D30, D40, D45, or D60. Ask this tool when the user wants to: · Examine the Navamsha (D9) for spouse, dharma, and chart corroboration. · Check the Dashamsha (D10) for career and professional life. · Validate dignity-in-varga for any planet (BPHS Ch. 6 Vimshopak principle). Returns: · facts.varga_type — the requested varga slug (e.g. 'd9') · facts.varga_lagna — ascendant sign in this varga · facts.planets — per-graha: sign, house, dignity, retrograde · facts.houses — per-house: sign, lord, lord_in, occupants · facts.reliability — 'reliable' | 'conditional' | 'requires_rectification' | 'unreliable' **Accepted varga_type values:** d1/rashi · d2/hora · d3/drekkana · d4 · d7/saptamsha · d9/navamsha · d10/dashamsha · d12 · d16 · d20 · d24 · d27 · d30 · d40 · d45 · d60/shashtiamsha. For full chart interpretation use `compute_chart`. For multi-varga yoga corroboration use `compare_schools`. Tier: All · Typical response: ~4 KB.

Describe a Jyotish school's calibration profile — its rule weights, dasha system, ayanamsha, divisional-chart usage, and signature techniques. Pure metadata — no chart needed. Ask this tool when the user wants: · Background on Parashari vs Jaimini vs KP vs Tajika vs Nadi. · School-specific calibration settings before running a chart. · Help choosing the right school for a given question. Returns: · facts.school_id, facts.dasha_system, facts.ayanamsha, facts.rule_weight_summary Recommended as the FIRST call in an agent session to ground the agent in the school it is about to read charts through (Parashari is the default). Tier: All · Typical response: ~1 KB.

Submit feedback on a chart / claim / explanation. Stored anonymously for engine improvement — no birth data is retained; the claim_id is the only correlator. Ask this tool when the user wants to: · Rate a chart's accuracy (1–5). · Flag a claim that seems off. · Suggest improvements to a verdict or narrative. Feeds the Calibratable Interpretive Layer (CIL) for school-weight tuning. Returns: · facts.acknowledged: true, facts.feedback_id Tier: All · Typical response: <1 KB.

Return engine + API version + protocol info. Unauthenticated — no API key required. Ask this tool to: · Verify the engine version your client is talking to. · Confirm wire compatibility (api_version CalVer). · Display a 'powered by KundaliMCP' line. Returns: · facts.engine_version, facts.api_version, facts.release_codename, facts.build Tier: All (no auth required) · Typical response: <1 KB.

No input parameters.

Return the complete Vimshottari dasha timeline from birth — all 9 mahadashas with nested antardashas (MD + AD by default). Ask this tool when the user wants to: · See every dasha period across their entire life. · Find Julian-Day (JD) + local + UTC boundaries for each period. · Build a multi-decade dasha calendar. Returns: · facts.periods — 9 mahadashas each with up to 9 antardasha sub_periods · facts.total_years — approximate lifetime span from birth · facts.dasha_system — always Vimshottari for this tool For the active dasha at a specific date with classical interpretation use `forecast_dasha`. For a full lifetime forecast with life-event scores use `compute_life_journey`. Tier: All · Typical response: ~36 KB.

API key format

Authorization: Bearer sutra_<32 hex chars>