Vedaksha
Vedaksha is an MCP server for Vedic astrology and astronomical ephemeris computations.
Compute natal charts (kundali) with planets, houses/cusps, aspects, dignities, ayanamsha, and configurable house systems.
Compute dashas across eight systems, plus karakas, combustion, vargas, shadbala, ashtakavarga, bhavas, drishti, and gochara.
Compute panchanga limbs and search ranked muhurta windows.
Compute transits and transit–natal aspects, and search exact transit events over time ranges.
Compute synastry and composite charts from planet longitudes.
Emit chart property graphs as Cypher, SurrealQL, JSON-LD, JSON, or RAG embedding text.
Accept UT1 Julian Days and sidereal ayanamshas, with location, elevation, and timezone options where relevant.
Supports deployment to Cloudflare Workers edge computing platform using the AnalyticalProvider ephemeris for zero-data environments.
Provides Docker container deployment for the MCP server with HTTP transport on port 3100.
Supports macOS arm64 platform with pre-built Python wheels available via PyPI installation.
Provides Python package distribution through PyPI for Python bindings installation and usage.
Provides Python bindings via PyO3 for chart computation and Vedic astrology functionality.
Provides native Rust crates for astronomical ephemeris computation and Vedic astrology platform functionality.
Provides WebAssembly bindings for browser-based chart computation with 972KB binary and zero data files.
Vedaksha: Rust ephemeris and Vedic astrology (Jyotish) engine
For developers building kundli (kundali) apps, panchang calendars and AI agents. Natal charts, dashas, vargas, shadbala and panchanga, computed from an ephemeris that agrees with JPL Horizons to 0.096″ mean in longitude, in Rust, Python and WebAssembly, and as 17 MCP tools. Clean-room: every algorithm is traced to a primary source. Source-available under BUSL-1.1, with no AGPL obligations; each release becomes Apache-2.0 four years after it ships.
Website · Docs · Playground · API reference · Blog
clean-room · 0.096″ mean longitude vs JPL Horizons · 1,625 tests (per push) + 24,350 oracle rows · MCP-native · BUSL-1.1 → Apache 2.0
Install · Quick start · Accuracy · What's inside · MCP + property graph · Provenance · FAQ · License
Install
Platform | Install | Notes |
Rust |
| full pipeline |
Python |
| engine via WebAssembly, |
WASM |
| browser & edge, no data files |
MCP |
| stdio + HTTP (bearer auth) |
Docker |
| multi-arch (amd64 + arm64) |
Compute janam kundali (natal charts), panchanga, dashas, nakshatras, vargas, shadbala, ashtakavarga, muhurta and transits/gochara from a sub-arcsecond ephemeris (JPL DE440s/DE441, worst case 0.272″ against Horizons) or from the data-file-free VSOP87A + ELP/MPP02 series (mean 0.160″, worst case 1.473″ over 1900–2025).
flowchart LR
K["JPL DE440s / DE441<br/>SPK kernel, ~31 MB"] --> E
V["VSOP87A + ELP/MPP02<br/>compiled to constants,<br/>no data files"] --> E
E["Ephemeris core<br/>precession · nutation<br/>light-time · deflection · ΔT"] --> W["Western<br/>houses · aspects<br/>dignities"]
E --> J["Jyotish<br/>nakshatras · dashas · vargas<br/>panchanga · shadbala · muhurta"]
W --> C["ComputedChart"]
J --> C
C --> G["Property graph<br/>Cypher · SurrealQL<br/>JSON-LD · RAG text"]
C --> M["MCP server<br/>17 tools · stdio + HTTP"]
C --> S["Rust · Python · WASM"]Related MCP server: Precision astronomical ephemeris and planetary positions via the Swiss Ephemeris.
Quick start
Python (pip install vedaksha): a sidereal (Lahiri) whole-sign chart, i.e. a kundli.
from vedaksha import Vedaksha
vk = Vedaksha()
chart = vk.natal_chart(julian_day=2451545.0, latitude=28.6139, longitude=77.2090,
ayanamsha="IndianOfficial", house_system="WholeSign")
print(chart["houses"]["asc"], [(p["name"], p["sign"]) for p in chart["planets"]])Rust (cargo add vedaksha):
use vedaksha::prelude::*;
fn main() {
// 2024-03-20 12:00 UT1. The day is a fraction: noon on the 20th is 20.5.
let jd = calendar_to_jd(2024, 3, 20.5);
let moon = apparent_position(&AnalyticalProvider, Body::Moon, jd).expect("in range");
println!("Moon {:.4}°", moon.ecliptic.longitude.to_degrees());
}A full chart, with houses and a sidereal zodiac, is the compiled doctest in crates/vedaksha/src/lib.rs.
JavaScript in the browser (npm install vedaksha-wasm; no data files):
import init, { compute_natal_chart } from "vedaksha-wasm";
await init();
const chart = JSON.parse(compute_natal_chart(JSON.stringify({
year: 2024, month: 3, day: 20, hour: 12, minute: 0, // UTC
latitude: 28.6139, longitude: 77.2090,
ayanamsha: "IndianOfficial", house_system: "WholeSign",
})));MCP (Claude Desktop claude_desktop_config.json, Cursor .cursor/mcp.json, or any stdio MCP client):
{
"mcpServers": {
"vedaksha": {
"command": "docker",
"args": ["run", "--rm", "-i", "ghcr.io/arthiqlabs/vedaksha-mcp", "--stdio"]
}
}
}Without Docker, cargo install vedaksha-mcp and set "command": "vedaksha-mcp" with no arguments, or pip install vedaksha and use vedaksha-mcp the same way.
Every Julian Day on the public surfaces is UT1, not TT and not TDB. The engine converts to TT internally for the dynamical terms and uses UT1 for Earth rotation, which fixes the ascendant, MC and all twelve cusps. Passing a TDB Julian Day adds ΔT worth of rotation instead of removing it — 0.289° (17.3′) at today's ΔT ≈ 69 s, on every cusp. Two exceptions say so in their names: the raw SPK query (state_vector), which indexes the kernel directly and takes TDB, and the Python binding's analytical_position(body, julian_day_tt), which takes TT.
Accuracy
These figures are reproducible, not just asserted: vedaksha-parity
is a separate harness (maintained by the same authors as this engine) that anyone can run against
their own copies of the reference kernels to check the published numbers below.
Every figure is printed by a named test. Reproduce the ephemeris tables with bash scripts/download_de440s.sh, then cargo test -p vedaksha-ephem-core --release -- --include-ignored --nocapture; the ayanamsha figures come from cargo test -p vedaksha-astro sidereal, and the cross-check against an independent Python derivation of the same primaries from cargo test -p vedaksha-astro --test ayanamsha_fixture.
What the headline 0.096″ measures — precisely. It is a mean apparent geocentric ecliptic-longitude residual, not a general position-accuracy figure: the fixture also carries ref_latitude, ref_distance and ref_speed, but oracle_comparison.rs marks them dead_code and none of the three enters this number. It covers the 1900–2025 rows, at 1,535 comparisons per body (15,350 total across 10 bodies). The full 1900–2100 grid of 24,350 rows has a mean of 0.088″ and the same worst row (see below); the 1900–2025 cut is kept so that the published count and definition do not change. And it compares against planetary-system barycentres, not physical planet centres, matching what the DE440s kernel stores and what SpkReader returns; querying centres instead would inject a spurious ~0.1″ offset for the outer planets (scripts/generate_horizons_oracle.py) — the same order of magnitude as the headline mean itself. These facts are also published as data in metrics.json's accuracy block (quantity, era, targetConvention), so the site renders them rather than anyone hand-copying this paragraph.
SpkReader vs JPL Horizons (DE441) — oracle_comparison.rs, 24,350 committed rows (10 bodies × 2,435 dates, 1900–2100). Horizons serves DE441, so this measures our DE440s pipeline against an independent kernel.
Era | Comparisons | Mean | Max |
1900–2025 | 15,350 | 0.096″ | 0.272″ (Moon, 1962-01-06) |
1900–2100 (all) | 24,350 | 0.088″ | 0.272″ (Moon, 1962-01-06) |
All 24,350 comparisons are within one arcsecond. Per body over 1900–2025 the mean runs from 0.092″ (Moon) to 0.100″ (Pluto), and the worst row of every body is between 0.243″ and 0.272″.
Time scale. Horizons' time tags are UT1 before 1962-01-20 and UTC from then. The oracle converts the UTC tags to TT with the leap-second count, as Horizons does itself, and reads the engine in TT, so neither ΔT nor UT1 − UTC is part of those rows' residual, and the oracle says nothing about ΔT there; earlier rows go through the engine's ΔT. Rows from 2026 on are compared the same way and are within 0.189″ (Moon, 2099-10-04). A Julian Day in UT1 after 2033.75 rests on an extrapolated ΔT (delta_t.rs), and one second of ΔT moves the Moon about 0.55″.
What the remaining 0.096″ is. After 1962 every body sits at 0.047″ to 0.054″ mean and at most 0.062″; before 1962 the bodies sit at 0.138″ to 0.146″ mean. That offset is shared by every body: it is the difference between Horizons' IAU 1976/1980 precession and nutation and the IAU 2006/2000B this engine uses. It is a difference of convention, and it is not emulated here. The largest row, the Moon on 1962-01-06, lies between 1962-01-01, where this engine hands ΔT from the SMH2016 spline to the USNO rows, and 1962-01-20, where Horizons switches from its pre-1962 series to its Earth-orientation file; the two series differ by 0.371 s across that handover, which is 0.2″ of Moon longitude (delta_t.rs). The Sun's light deflection of the planets is applied (solar_deflection_oracle.rs).
AnalyticalProvider vs JPL Horizons — analytical_oracle.rs, 1900–2025: overall mean 0.160″, worst case 1.473″ (Neptune, 2025-09-02), Moon 0.094″ mean via ELP/MPP02 (0.055″ after 1962). 13,815 comparisons across 9 bodies (1,535 dates per body) over 1900–2025; see metrics.json's accuracy.analytical block. The same run over all 21,915 comparisons to 2100 has a mean of 0.251″ and a worst case of 2.248″ (Neptune, 2078-01-27); metrics.json does not publish that pair.
Per body, because the mean hides a pattern worth knowing before you pick this provider:
body | mean″ | body | mean″ |
Sun | 0.094 | Jupiter | 0.148 |
Moon | 0.094 | Saturn | 0.159 |
Mercury | 0.094 | Uranus | 0.257 |
Venus | 0.094 | Neptune | 0.410 |
Mars | 0.090 |
The Sun, the Moon and the inner planets sit in a tight band at 0.090″ to 0.094″ and the error then grows outward. Split at 1962-01-20, all nine bodies sit at 0.131″ to 0.153″ mean before it, the same frame offset the SPK path shows. After it the Sun and the inner planets are at 0.038″ to 0.039″, the Moon at 0.055″, and Jupiter, Saturn, Uranus and Neptune at 0.165″, 0.165″, 0.365″ and 0.660″.
That growth belongs to the theory, not to how the tables are cut. scripts/generate_vsop87a.py drops terms below a uniform absolute amplitude of 1e-7 AU, but evaluating the complete untruncated VSOP87A series gives the same outer-planet residuals as the committed tables to four decimals (measured on geometric heliocentric vectors against DE440s over 1900–2100; the notes on VSOP87A_TO_EQUATORIAL in crates/vedaksha-ephem-core/src/analytical/mod.rs have the table). The authors fitted the theory to the JPL integration DE200, not to DE440 (vsop87.doc, "PRECISION"), and that is what the residual measures. If you need the outer planets to sub-0.1″, use SpkReader, where they are no worse than the inner bodies: Jupiter and Saturn are 0.096″ mean against the same oracle, inside the 0.092″ to 0.100″ band of every other body.
Until 2026-08-20 the analytical figures were an order of magnitude worse, and this README attributed the gap to VSOP87A being a truncated theory. That was wrong, and the wording protected a defect of ours: the analytical provider answered EarthMoonBarycenter with VSOP87A's Earth-centre series, so the observer sat 4,671 km off, and earth_state divided a barycentre-relative Moon by 1 + EMRAT instead of EMRAT for a further 56.8 km. Both are fixed; the figures before and after are in CHANGELOG-v6.1.0.md.
The SPK and analytical figures above are the v10.0.0 measurement, the same run that metrics.json and vedaksha.net/accuracy publish. The figures it replaced, and their causes, are in CHANGELOG-v10.0.0.md: ΔT read from the measurements and the published predictions, 30 corrected nutation rows, the Sun's light deflection of the planets, VSOP87A rotated by the matrix its authors publish, and an oracle that compares Horizons' UTC tags in TT. One body is worse at its maximum than before: analytical Uranus, now 1.201″, although its mean improved.
ELP/MPP02 Moon — lunar_horizons.rs: 0.015″ at J2000, 0.020–0.053″ across 1500–2500 CE.
What is not measured
House cusps are not validated against any external reference.
No ayanamsha is validated against another implementation, and that is deliberate. All eleven are derived forward from a primary — a chapter, a committee, a proposer's own paper, or a star catalogue — and each reproduces its own anchor to 1e-9° and, where its primary documents one, its own zero year. What is not claimed is agreement with anyone else's numbers: comparing against them would be the reverse-engineering this re-derivation exists to undo. See
docs/audit/2026-08-17-ayanamsha-cleanroom/.Dasha, nakshatra and shadbala tests check the text's own rules, not an external comparison: they verify that BPHS constants sum to 120 years, that boundaries tile the circle, and that shadbala parts come out as the verses' formulas give them when worked by hand. No dasha period or shadbala figure is compared with another implementation's output.
The library's coarse shadbala form is partial.
compute_shadbala_fullcarries four of Sthana Bala's five parts (Uchcha, Ojhayugma, Kendradi and Drekkana, without Saptavargaja) and only Nathonnata and Paksha of Kala Bala, as 0-or-30 steps; its Cheshta, Dig and Drik grades are not the verses'. The complete form,compute_shadbala_complete(BPHS 27, part by part, with an option wherever the text leaves a parameter open), is what the MCPcompute_shadbalatool and the WASM export serve.
Technical report
A full write-up of both ephemeris pipelines, their measured accuracy, and the clean-room
provenance of every algorithm: docs/paper/main.tex (build with
make -C docs/paper pdf, requires tectonic).
It goes well beyond the summary above, and reports several things that are stated nowhere else:
Cross-validation against two national-agency ephemerides, measured with a separate parity harness maintained by the same authors (not a third party), from two different agencies (JPL DE440 and IMCCE INPOP21a), rather than agreement with JPL alone.
Analytical-path accuracy across 1550–2650 CE, per body and per century-band of distance from J2000, with the time scale removed from the comparison by addressing both sides in TT so that ΔT divergence cannot contaminate the residual.
Component-level validation of the SPK reader against another implementation's read of a comparable kernel, isolating the DAF/SPK parser and Chebyshev evaluation from the apparent-place pipeline layered on top.
A methodological note on reproducibility: bit-level output is architecture-scoped, because the SIMD trigonometric kernel maps to one AVX2 register but two NEON registers. Accuracy is not — measured identical to a milliarcsecond on both. (Since v10.0.0 the lunar series alone no longer calls that kernel and is bit-identical on both architectures; the whole analytical provider still is not.)
What is not validated, stated plainly, including house cusps, the true node, and every ayanamsha.
Status: not peer reviewed, and not submitted anywhere. It is a technical report, not a preprint. Every measured figure in it is specific to the engine version named on its title page.
What's inside
Two ephemeris providers. SpkReader reads JPL DE440s (~31 MB) for sub-arcsecond work. AnalyticalProvider compiles VSOP87A + ELP/MPP02 to constants and needs no data files — for WASM, edge and Cloudflare Workers. ChebyshevProvider is an opt-in provider that fits the same series per segment with Chebyshev polynomials (within 0.1 m for the Moon and 3 m for a planet, over the whole range) for workloads that ask for many nearby times; AnalyticalProvider stays the exact series.
Speed. On one Apple M5 Pro (Criterion medians, v10.0.0): an analytical Moon in 56 µs, a nine-body apparent-place chart in 0.97 ms, the Sun in 2.9 µs; 3.3, 3.8 and 2.1 times v9.4.1. Twenty 30-day muhurta searches and five one-year transit scans over MCP take 0.46 s, where v9.4.1 took 17.5 s. The series are evaluated in full, and the one interpolated path (the walk the scans read) stays within 5e-5″ of the direct computation; how each was done, and the full table, are in CHANGELOG-v10.0.0.md.
Jyotish, from primary sources. 27 nakshatras with padas and lords · 8 dasha systems (Vimshottari, Ashtottari and Yogini, which runs beyond its first round; the rashi dashas Chara, Narayana, Sthira, Niryana Shoola and Maheshwara) · all 16 vargas (D-1 → D-60) · the complete shadbala of BPHS 27 with Ishta/Kashta phala, bhava bala (27.26 to 31) and vimshopaka bala (all four schemes) · 11 ayanamshas, each traceable to a chapter, a star or a committee · panchanga's five limbs, with vara reckoned from local sunrise and Rahu/Gulika Kalam as real time windows · graded and degree-wise (sputa) drishti per BPHS Ch. 26 · four upagrahas (Kala, Mrityu, Ardhaprahara, Yamaghantaka) · mean, true and osculating nodes, all referred to the ecliptic of date, with the J2000 variant tracking DE441's OM to 0.6″ (KP sub-lord ready).
Sky events, in the vedaksha-vedic crate. Solar and lunar eclipses, every sign ingress and retrograde station of a graha in a range, heliacal rising and setting by the Surya Siddhanta's kalamsha, amanta and purnimanta lunar months with adhika and kshaya, and tithi, nakshatra, karana and yoga ends and sankrantis timed to the resolution of a Julian Day. Long scans read the Moon and the Sun from an interpolated walk (walk::BodyWalk, vedaksha_vedic::walked::WalkedSky) within 5e-5″ for the Moon and 1e-5″ for the Sun of the direct computation; the planets are not walked.
Western: calculation, not interpretation. 10 house systems, major aspects with applying/separating motion, essential dignities, synastry and composite. ChartConfig defaults to tropical. There is no Western interpretive layer and no parity with the Jyotish surface.
Crates, published to crates.io in lockstep: vedaksha (umbrella, 7 locales) · -math · -ephem-core · -astro · -vedic · -graph · -mcp.
MCP + property graph
17 tools, discoverable with a single tools/list. The catalog is generated from the Rust definitions and locked by a snapshot test, so it cannot silently drift from the code. compute_dasha serves the eight dasha systems above. compute_shadbala takes a moment and a place (julian_day, latitude, longitude and a sidereal ayanamsha), casts the chart itself and returns every part of BPHS 27 for the seven grahas.
compute_natal_chart · compute_dasha · compute_vargas · compute_karakas · compute_combustion · compute_shadbala · compute_ashtakavarga · compute_transit · compute_gochara · search_transits · search_muhurta · compute_panchanga · compute_drishti · compute_bhavas · compute_synastry · compute_composite · emit_graph
Any chart converts to a property graph via emit_graph or vedaksha_graph::chart_to_graph, emitting Cypher, SurrealQL, JSON-LD, JSON or RAG embedding text. An agent can then ask "which planets aspect the 7th-house lord?" as a graph query instead of re-implementing chart logic. Computations themselves return typed structs; the graph is a projection you ask for.
What a chart actually yields: 4 of the ontology's 9 node types (Chart, Planet, Sign, House) and 7 of its 12 edge types. Nakshatra, Pada, Pattern, DashaPeriod and FixedStar are defined in vedaksha_graph::ontology but are not built from a ComputedChart, which does not carry the data they need. Compute those through their own APIs.
VEDAKSHA_MCP_TOKEN=… vedaksha-mcp --http --port 3100HTTP mode requires Authorization: Bearer <token> on every POST and refuses to start without VEDAKSHA_MCP_TOKEN, unless you pass --insecure-no-auth for a trusted network. /health and the informational GET stay open.
Clean-room provenance
Every implemented algorithm carries a // Source: doc-comment naming its primary paper or treatise — VSOP87A, ELP/MPP02, IAU standards, BPHS, Jaimini. Two subsystems have been re-derived from primary sources behind a documented firewall, and each ships its own audit directory: the lunar theory (2026-05-09) and the sidereal surface (2026-08-17). Each records the primaries, the process, what was searched and rejected, and a generator that re-derives the values so the claim can be re-run rather than taken on trust. See also DATA_PROVENANCE.md. This is the evidence a BUSL-1.1 licensee can audit.
In production
Product | What it is |
Agentic-AI Jyotish MCP with the full computation suite. Builds directly on the | |
Consumer endpoint — chat-based readings and self-serve PDF reports. |
FAQ
What is Vedaksha?
A Rust engine for astronomical ephemeris and Vedic astrology (Jyotish), with Python and WebAssembly bindings and an MCP server of 17 tools for AI agents. It computes planetary positions, natal charts, panchanga, dashas, vargas and shadbala.
Can it compute a kundli (kundali, janam kundali)?
Yes. Pass a sidereal ayanamsha, for example IndianOfficial (Lahiri), with a house system such as WholeSign. The MCP tools and the Python binding default to tropical, so a kundli needs the ayanamsha stated; the WASM compute_natal_chart defaults to IndianOfficial.
Is it free to use? Is it AGPL?
It is not AGPL, and it contains no AGPL code. It is source-available under BUSL-1.1: non-commercial use is free; commercial use (a product or service earning revenue from external customers) needs a one-time licence of USD $500 per organisation, covering that version and every later one. Each release converts to Apache-2.0 four years after it ships. BUSL is not an OSI open-source licence.
Does it need ephemeris data files?
No. AnalyticalProvider evaluates VSOP87A and ELP/MPP02 compiled into the binary, which is what the WASM package and the MCP server use. SpkReader reads a JPL DE440s kernel (~31 MB, fetched by scripts/download_de440s.sh) for the highest accuracy.
How accurate is it?
Against JPL Horizons over 1900 to 2025, in apparent geocentric longitude: 0.096″ mean and 0.272″ at worst on the SPK path, 0.160″ mean and 1.473″ at worst on the analytical path. House cusps are not validated against an external reference; see Accuracy.
Which ayanamshas and dasha systems are supported?
Eleven ayanamshas, each derived from a primary source, and eight dasha systems: Vimshottari, Ashtottari, Yogini, Chara, Narayana, Sthira, Niryana Shoola and Maheshwara.
Can an AI agent use it?
Yes. The MCP server runs over stdio or HTTP and is listed in the official MCP Registry as io.github.arthiqlabs/vedaksha-vedic-astrology. See Quick start for a client config.
License
Business Source License 1.1 — SPDX BUSL-1.1, which is what crates.io, PyPI and npm display.
Non-commercial — free (personal, research, education, internal tools).
Commercial — $500, charged once per organization. Unlimited products and seats, perpetual, and it covers the version you license and every version released after it — not charged again per release. Purchase →
Converts to Apache 2.0 four years after each version's release. That future licence text is kept at
CHANGE-LICENSE.txt— it is the Change License in BUSL terms, not a licence you may choose today.
See LICENSE, SECURITY.md, CONTRIBUTING.md and MAINTENANCE.md.
Copyright © 2026 ArthIQ Labs LLC · Licensed under the Business Source License 1.1 (BUSL-1.1).
Available Tools
17 toolscompute_ashtakavargaARead-only
Compute Bhinna Ashtakavarga (raw bindu tables) and Sarvashtakavarga for all 7 planets from sign positions. Source: BPHS Ch.66 vv.13-68. Trikona/Ekadhipatya Shodhana and Pinda Sadhana are not included.
Inputs: sun (required), mars (required), moon (required), lagna (required), +4 more. Returns: tables, sarvashtakavarga
compute_bhavasARead-only
Compute the whole-sign bhava (house) chart from an ascendant. In the Vedic whole-sign system the entire sign containing the ascendant is the 1st bhava, the next sign the 2nd, and so on — houses do not have cusps within signs. Returns the sign of each of the twelve bhavas with its kendra / trikona / dusthana / upachaya classification, and optionally places supplied grahas into their bhavas.
Inputs: ascendant (required), planets. Returns: houses, planets, lagna_sign
compute_combustionARead-only
Compute combustion state for each planet relative to the Sun: principle per BPHS Ch.7 vv.28-29, orbs per Surya Siddhanta IX.6-8 and X.1 (Moon 12, Mars 17, Mercury 14 or 12 retrograde, Jupiter 11, Venus 10 or 8 retrograde, Saturn 15 deg). Returns Combust, DeeplyCombust, or None for Moon, Mars, Mercury, Jupiter, Venus, Saturn with degrees of separation. This is a low-level tool over already-known positions, not a natal-chart tool: call compute_natal_chart first and pass its planets[].longitude (matched by planets[].name) and planets[].retrograde values straight through as this tool's inputs — do not recompute or re-derive them.
Inputs: sun (required), mars (required), moon (required), venus (required), +8 more. Returns: states
compute_compositeARead-only
Compute the midpoint composite chart of two charts: for each graha, the shorter-arc midpoint of its longitude in the two charts, and the arithmetic mean of its two speeds. The two charts must carry the SAME graha names — each graha is paired with its namesake, not with whatever happens to sit at the same position in a list — and a name present in one chart but not the other is an error naming that graha. Longitudes only: this tool needs no birth time, place or ephemeris.
Inputs: chart_a (required), chart_b (required). Returns: planets
compute_dashaARead-only
Compute Vedic dasha (planetary period) sequences. Supports eight classical systems: Vimshottari, Ashtottari, Yogini (Moon-longitude based, require moon_longitude); Chara, Narayana (sign based, require BOTH lagna_sign AND graha_signs, since each sign's period length is counted to the sign its lord occupies in this chart); Sthira, NiryanaShoola (niryana_shoola is accepted too) and Maheshwara (Jaimini rashi dashas, require lagna_sign AND graha_longitudes, since the atmakaraka and the tie-breaks of the strength tests read degrees). graha_signs takes the eight sign_index values compute_natal_chart already returns, graha_longitudes the eight sidereal longitudes; Ketu is derived from Rahu and must not be supplied. Yogini takes rounds (1 to 10 whole 36-year rounds) or until (a horizon Julian Day); Chara takes antardashas (twelve per period, BPHS 51.5-51.9). Sthira, NiryanaShoola and Maheshwara use the defaults of the vedic crate's dasha functions (see their module docs) and always carry their antardashas. Sthira and Maheshwara start from the Brahma graha; a chart whose marks leave none returns no_brahma: true with a message, not an error. Returns a JSON dasha tree with start/end Julian Days.
Inputs: birth_jd (required), until, levels, rounds, +7 more. Returns: Envelope depends on `system`; see the four variants below. Every period carries…
compute_drishtiARead-only
Compute graha drishti — Vedic sign aspects — for all nine grahas. Unlike Western aspects, drishti is cast from sign to sign and is asymmetric: every graha aspects the 7th from itself, and Mars additionally aspects the 4th and 8th, Jupiter the 5th and 9th, Saturn the 3rd and 10th. Returns each aspect with its graded strength (Full, ThreeQuarter, Half, Quarter) and the house distance.
Inputs: sun (required), ketu (required), mars (required), moon (required), +5 more. Returns: aspects
compute_gocharaARead-only
Compute Gochara (transit interpretation) for the seven grahas against a natal reference sign per BPHS Ch.29. Returns favourable/unfavourable verdict, house from natal, and raw vedha (obstruction) candidates per planet. The natal reference sign is the caller's choice — typically the natal Moon's sign (Chandra Gochara) or the natal Lagna's sign. Rahu and Ketu are not included.
Inputs: sun (required), mars (required), moon (required), venus (required), +6 more. Returns: entries
compute_karakasARead-only
Compute Jaimini Chara Karaka assignments from sidereal planet longitudes. Ranks planets by degrees within their current sign: highest = Atmakaraka (soul significator), lowest = Darakaraka (spouse significator). Supports 7-karaka (Sun–Saturn) and 8-karaka (adds Rahu) schemes.
Inputs: sun (required), mars (required), moon (required), venus (required), +5 more. Returns: karakas
compute_natal_chartARead-only
Compute a natal astrological chart for a given time and location. Returns JSON with each body's longitude, latitude, speed, sign, house, dignity and retrograde flag, the house cusps with ascendant and MC, the aspects, and the ayanamsha applied. Pass a sidereal ayanamsha for a Vedic chart (kundali); the default is tropical. To get a property graph, pass this output to emit_graph.
Inputs: latitude (required), longitude (required), julian_day (required), ayanamsha, +1 more. Returns: houses, aspects, planets, julian_day, +2 more
compute_panchangaARead-only
Compute the panchanga — the five limbs of the Vedic almanac — for an instant: tithi (lunar day, with paksha and lord), vara (weekday reckoned from local sunrise, with its lord and the Rahu and Gulika Kalam windows as Julian Days), nakshatra (with pada), yoga (one of the 27 nithya yogas, with degrees remaining), and karana (half-tithi). Takes sidereal longitudes; all returned instants are Julian Days (UT). vara.from_sunrise reports HOW the weekday was reckoned: true means it was taken from an actual local sunrise (the Vedic definition); false means no sunrise exists to reckon from — the polar day or polar night, above about ±66.5° latitude — and the value is the observer's local CIVIL weekday as a documented fallback, which is a different quantity. Check it before presenting the vara at high latitude. vara.rahu_kalam being null is NOT the same signal: the Kalam windows can also be null while from_sunrise is true.
Inputs: jd (required), sun (required), moon (required), latitude (required), +3 more. Returns: vara, yoga, tithi, karana, +1 more
compute_shadbalaARead-only
Compute the complete six-fold Shadbala of the seven grahas (Sun to Saturn) for a birth moment and place, per BPHS Ch.27, with Ishta and Kashta Phala per Ch.28, in virupas. Pass the moment and the place; the tool casts the chart itself and reads sunrise, sunset and the next sunrise from the engine. Every part is in the output, each in its own field: Sthana (uccha, saptavargaja, ojhayugma, kendradi, drekkana), Dig (continuous, the arc from the weak cusp over 3, 27.7), Kala (nathonnata, paksha, tribhaga, abda, masa, vara, hora, ayana and yuddha, which is signed), Cheshta (the cheshta kendra for Mars to Saturn, the Sun's ayana and the Moon's paksha bala, 27.18 and 27.24-25), Naisargika and Drik (a quarter of the benefic sphuta drishti added, a quarter of the malefic taken away, the aspect of Mercury and Jupiter added whole, 27.19; it can be negative or pass 60). The Sun's ayana and the Moon's paksha bala are counted once in kala and once in cheshta, each undoubled. The rules are the verses' defaults; the benefic and malefic grahas are those of BPHS 3.11, with Rahu (the mean node) and Ketu counting only as malefic company for Mercury. Each graha also carries its motion state (vakra, anuvakra, ... atichara, 27.21-23) against the mean geocentric motion; it is reported beside the strengths and is not part of any total. The Sun must both rise and set at the place: in the polar day or night there is no Hindu day to divide into thirds and horas, and the call fails by name.
Inputs: latitude (required), ayanamsha (required), longitude (required), julian_day (required), +3 more. Returns: cusps, moment, planets, julian_day, +3 more
compute_synastryARead-only
Compute synastry — the aspects each graha in one chart makes to each graha in another chart. Every graha in chart A is tested against every graha in chart B (the two charts do not need the same graha names), and each hit is returned with its aspect type, orb in degrees and strength (1.0 at exact, falling linearly to 0.0 at the orb boundary). Orbs are the traditional Lilly values — conjunction, trine and opposition 8°, square 7°, sextile 6°, minors 2° — scaled by orb_factor. Longitudes only: this tool needs no birth time, place or ephemeris.
Inputs: chart_a (required), chart_b (required), aspect_set, orb_factor. Returns: aspects
compute_transitARead-only
Compute transiting planet positions relative to a natal chart at a specific moment. Returns planet longitudes for the transit time alongside natal positions, enabling aspect calculation between transit and natal placements.
Inputs: natal_jd (required), natal_lat (required), natal_lon (required), transit_jd (required). Returns: natal_jd, transit_jd, natal_positions, transit_positions, +1 more
compute_vargasARead-only
Compute Vedic divisional charts (vargas). Given a time and place, returns one chart per requested division: the varga lagna, and for each of the ten bodies compute_natal_chart returns — the seven grahas plus the mean, true and osculating lunar node — its rashi longitude, the sign it occupies within that varga, its dignity in that sign, and its whole-sign bhava counted from the varga lagna. Ketu is not listed separately: it is the node's opposite point, 180 degrees away. The nodes carry no dignity, so that field is absent for them. Supply planet_longitude instead to divide a single longitude without an ephemeris lookup, in which case no graha name, dignity or bhava is returned because none is defined. Vargas are classically read on a sidereal zodiac: pass an ayanamsha, or accept the Tropical default this surface uses everywhere. Source: BPHS Ch. 6-7.
Inputs: latitude (required), divisions (required), longitude (required), julian_day (required), +3 more. Returns: vargas, tradition, julian_day, true_ayanamsha_value
emit_graphARead-only
Turn a chart into a queryable property graph. Accepts the output of compute_natal_chart directly (pass latitude and longitude alongside it), or an existing ChartGraph. Emits Neo4j Cypher, SurrealDB SurrealQL, JSON-LD, plain JSON, or RAG embedding text.
Inputs: format (required), chart_json (required), latitude, longitude, +1 more.
search_muhurtaARead-only
Search for auspicious time windows (muhurta) within a given period for a geographic location. Returns ranked muhurta candidates with quality scores based on tithi, nakshatra, yoga, karana, and planetary positions. The search window is capped at 30 days (see MUHURTA_SEARCH_RANGE_TOO_LARGE), a scope limit; for a longer horizon, issue several searches.
Inputs: end_jd (required), latitude (required), start_jd (required), longitude (required), +3 more. Returns: end_jd, results, latitude, start_jd, +4 more
search_transitsARead-only
Search for transiting planet–natal planet aspects within a time window. Supply natal positions and a Julian Day range; receive a list of exact transit moments with aspect type, orb, and applying/separating status.
Inputs: end_jd (required), start_jd (required), natal_positions (required), bodies, +2 more. Returns: end_jd, events, max_orb, start_jd, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools target clearly different computations (dasha, shadbala, panchanga, ashtakavarga, karakas), and descriptions explicitly disambiguate close pairs like compute_transit vs search_transits (positions vs exact aspect moments) and compute_drishti vs compute_synastry (intra-chart sign aspects vs inter-chart aspects). The only residual overlap is conceptual: compute_transit vs compute_gochara both concern transits, and compute_natal_chart vs compute_bhavas both involve houses, so an agent may briefly hesitate before selecting.
All 17 names are snake_case with a clear verb_noun shape: 13 compute_* tools, 2 search_* tools, and emit_graph. The pattern is predictable and immediately readable, with no camelCase or stylistic mixing.
17 tools is on the upper edge but each corresponds to a genuinely distinct Vedic computation (vargas, dasha, shadbala, combustion, ashtakavarga, gochara, panchanga, drishti, bhavas, synastry, composite, transits, muhurta, graph export). The surface is broad and no tool feels decorative, though it is slightly heavy for easy scanning.
The surface covers the full lifecycle from natal chart construction through derived analyses (vargas, karakas, dashas, shadbala, ashtakavarga), prediction (transits, gochara, muhurta), and export (emit_graph). Minor gaps remain: no explicit yoga/combination detection, and ashtakavarga explicitly omits Trikona/Ekadhipatya Shodhana and Pinda Sadhana, but agents can work around these.
Maintenance
Related MCP Connectors
Professional Vedic astrology tools for AI agents via MCP.
MCP server for aerospace calculations: orbital mechanics, ephemeris, DSN operations, ...
Vedic kundli, panchang, dashas, nakshatras and KP charts for AI agents, one API key.
Vedic astrology and ephemeris engine calibrated to Swiss Ephemeris and Jagannatha Hora.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceWorld's first Vedic Astrology MCP Server — connect Claude, ChatGPT, Cursor, or any AI to real Vedic astrology. Provides horoscope predictions, compatibility matching, numerology, planetary positions, yogas and house analysis via MCP.11-
- AlicenseNot gradedqualityDmaintenanceA self-contained MCP server that gives AI agents the ability to calculate high-precision astronomical data. It provides tropical zodiac coordinates, planetary speeds, retrograde detection, and house cusps using the trusted Swiss Ephemeris engine. 100%4AGPL 3.0
- AlicenseAqualityCmaintenanceAstrology MCP server that computes natal charts, transits, synastry, progressions, returns, eclipses, retrogrades, and moon phases from a real ephemeris, enabling AI agents to provide accurate astrological calculations without hallucination.1275 npm1MIT
- FlicenseNot gradedqualityDmaintenanceA Vedic astrology MCP server that computes birth charts, dashas, transits, and yogas locally using Swiss Ephemeris, enabling an LLM to interpret horoscopes and provide personalized advice.-