kshana 0.14.1 → 0.15.0

package/README.md

@@ -43,7 +43,7 @@ citable table in [`docs/PROVENANCE.md`](docs/PROVENANCE.md).
 *Free and open source under Apache-2.0, professionally developed and maintained by
 Ashforde OÜ — commercial support, integration, and proprietary extensions available.*
 
-> **Status: v0.14.1 · a simulation substrate, not yet a product.** A validated,
+> **Status: v0.15.0 · a simulation substrate, not yet a product.** A validated,
 > fully reproducible engine spanning the PNT stack — orbit geometry and constellation
 > design, a numerical (Cowell) propagator with a six-perturbation force model, maneuver
 > and trajectory design, time systems, inertial navigation (incl. map-aided and
@@ -303,6 +303,29 @@ const result = JSON.parse(run(tomlText));
 console.log(version(), result.classical.fom.timing_p95_ns);
 ```
 
+### AI agents (MCP)
+
+Kshana ships an [MCP](https://modelcontextprotocol.io) server, [`kshana-mcp`](mcp/kshana-mcp/),
+so AI assistants and agents can run the **validated** engine instead of guessing the
+math — usable from **Cursor, JetBrains AI Assistant / Junie, and any MCP-compatible
+assistant or agent**. It exposes `run_scenario`, `list_scenario_kinds`,
+`validate_scenario`, `export_sp3`, and `export_omm` (each a thin wrapper over
+`kshana::api`).
+
+```bash
+cargo install kshana-mcp                          # crates.io
+docker run --rm -i ghcr.io/ashfordeou/kshana-mcp  # or OCI, no Rust toolchain
+```
+
+Then register `kshana-mcp` in your client's `mcpServers` config — see
+[`mcp/kshana-mcp/README.md`](mcp/kshana-mcp/README.md) for per-client snippets. The
+server is a standalone, workspace-excluded crate (the `rmcp` SDK is edition 2024), so it
+never affects the lean published `kshana` crate or its build.
+
+**In a JetBrains IDE** you can also install the **Kshana** plugin from the JetBrains
+Marketplace (Settings → Plugins → search "Kshana") to run scenarios from a right-click —
+see [`ide/jetbrains/`](ide/jetbrains/).
+
 ## Scenario format
 
 Scenarios are declarative TOML. A top-level `kind` selects the pack (`clock` is
@@ -715,7 +738,7 @@ entry for every user-visible change. Participation is governed by our
 
 If you use Kshana in academic or technical work, please cite it. Machine-readable
 metadata is in [`CITATION.cff`](CITATION.cff) (GitHub renders a "Cite this repository"
-button from it); cite the version you used (e.g. `v0.14.1`) together with the
+button from it); cite the version you used (e.g. `v0.15.0`) together with the
 scenario and seed for full reproducibility. Every release is archived on Zenodo with
 a citable DOI — the concept DOI [10.5281/zenodo.20528627](https://doi.org/10.5281/zenodo.20528627)
 always resolves to the latest version.

package/package.json

@@ -5,7 +5,7 @@
     "Chakshu Baweja <contact@ashforde.org>"
   ],
   "description": "Open, reproducible PNT-resilience simulator with quantum-sensor performance models",
-  "version": "0.14.1",
+  "version": "0.15.0",
   "license": "Apache-2.0",
   "repository": {
     "type": "git",
@@ -17,7 +17,7 @@
     "kshana.d.ts"
   ],
   "main": "kshana.js",
-  "homepage": "https://github.com/AshfordeOU/kshana",
+  "homepage": "https://kshana.dev",
   "types": "kshana.d.ts",
   "sideEffects": [
     "./snippets/*"