Vedic astrology computation
reimagined from first principles.
KundaliMCP is the first agentic-AI-native Jyotish computation platform — a Model Context Protocol toolkit that gives AI agents the ability to cast, analyze, and interpret kundali charts with full deterministic transparency. Not a chatbot wrapper. Not a lookup table. A computational engine that models the full complexity of Jyotish as a graph problem.
A computation engine, not a chatbot.
Existing Jyotish software treats chart computation as a solved problem and interpretation as a black box. KundaliMCP treats both as engineering problems. Computation is a graph traversal, not a lookup table. Interpretation is deterministic rule application, not LLM hallucination.
Every conclusion has a provenance chain back to the astronomical facts. Every rule carries its classical citation — no silent assumptions. The same input always produces the same output from the deterministic layer; the interpretive layer is tunable but never touches the astronomical foundation.
The technologies of 2026 — defeasible reasoning engines, the MCP protocol, and full-fidelity astronomical compute on commodity hardware — make it feasible to model Jyotish rigorously and transparently: every interpretation defeasibly reasoned, traced to a classical rule, and that rule traced to its source text.
Agents call compute_chart, explain, forecast_events — and get back fully traceable, source-cited results in seven languages, grounded in classical texts.
Why KundaliMCP is different.
The layers inside the binary.
One statically-linked Rust binary, built from named internal layers — a clean-room ephemeris at the bottom, compute primitives and the defeasible reasoning engine in the middle, a compile-time-baked localization ontology on top, all fronted by a wasm32 edge gateway.
Checked against the texts, not against a metric.
There is no accuracy oracle. Correctness of every rule means faithfulness to its classical source, verified by reading the encoding against the text. What can be measured mechanically, is — with re-runnable checks in the repo.
Every rule cited. No silent assumptions.
Every life-event trigger, yoga definition, and dasha rule in the engine is derived from a named classical source — not from a prior-generation reference and not from convention. If a source contradicts another, both are recorded with attribution.
Built for builders.
AI agent builders
Add classical Jyotish computation to any MCP-compatible agent — Claude, ChatGPT, LangChain, CrewAI, AutoGen, or your own. The protocol is the product; no adapter layer, no SDK, no glue code.
Jyotish software developers
Use KundaliMCP as a computation backend. 17 tools, all 5 dasha systems, all 16 divisional charts, 7 languages — production-ready today.
Researchers
Study traditional knowledge systems with modern computational tools. Every rule is cited; the same input always produces the same deterministic-layer output.
Practitioners
Transparent classical analysis. See the provenance chain behind every interpretation. No black boxes. No silent assumptions.
ArthIQ Labs
Human intent, meets AI-native execution.
ArthIQ Labs is an AI-native incubation studio, built on agentic engineering. Coding agents handle first-pass execution across the software lifecycle; humans own architecture, tradeoffs, and outcomes.
The work of a quarter, in a week. Live products at roughly a tenth the cost of a traditional team. No concept decks, no endless pilots — concept to launch in 7–21 days.
Visit arthiq.net →Strategy, architecture, and roadmapping for AI-native businesses.
End-to-end design and shipping of AI-native products. Concept to launch in 7–21 days.
Operations, support, and agentic process automation for AI systems in production.
Ready to add Jyotish to your agent stack?
Get a key in 60 seconds. No credit card required for the compute API. 17 tools, 7 languages, every rule source-cited — live at mcp.kundalimcp.com/mcp.