Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Descripción del creador (original en inglés)
Warhammer 40K and Kill Team rules, stats, and game flow MCP server
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"warhammer-oracle": {
"command": "npx",
"args": [
"-y",
"warhammer-oracle"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add warhammer-oracle -- npx -y warhammer-oraclePégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"warhammer-oracle": {
"command": "npx",
"args": [
"-y",
"warhammer-oracle"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"warhammer-oracle": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"warhammer-oracle"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub gregario, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.1.1) llegó al registro hace 8 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js en tu computadora.
En la misma categoría: Spec Driven Development, Remote Desktop Commander, Dialyne
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Real phone calls in France for AI agents: dial +33 numbers, menus, hold, AI disclosure.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Warhammer Oracle Warhammer 40K rules, unit stats, and game flow. An MCP server.
Ask your AI assistant about datasheets, stratagems, detachments, enhancements, keywords, phase sequences, wound math, and more. Covers Warhammer 40,000 (10th and 11th Edition), Combat Patrol, and Kill Team.
Editions: 40K unit/detachment/enhancement lookups default to 11th Edition. Pass game_mode: "40k_10e" to any tool for 10th Edition data instead — 10th Edition support isn't going away. Turn sequences/phases, core keywords, and Core Stratagems are hand-curated from the 11th Edition Core Rules. Detachment-specific stratagems are hand-curated per faction, layered the same way the tabletop rules are layered: an 11th Edition Faction Pack detachment overrides the base Codex where the pack details it in full, and the unrevised Codex baseline applies everywhere else.
npx warhammer-oracle
Or install globally:
npm install -g warhammer-oracle
Add to your claude_desktop_config.json:
{
"mcpServers": { "warhammer-oracle": { "command": "npx", "args": ["-y", "warhammer-oracle"] } } }
claude mcp add warhammer-oracle -- npx -y warhammer-oracle
lookup_unitLook up a unit datasheet by name. Returns stat profiles, unit size (model count), ranged and melee weapons, abilities, and keywords.
"Look up the Intercessor Squad datasheet"
"What are the stats for a Leman Russ Battle Tank?"
When a name has different datasheets, the tool lists the matching factions. If a name and faction still have multiple datasheets, it also lists their IDs; pass the faction and one datasheet_id back to select it.
Parameters: unit_name (required), faction (optional), datasheet_id (optional, exact ID shown for same-faction variants), game_mode (optional: 40k/40k_11e (default, 11th Edition), 40k_10e, combat_patrol, kill_team)
lookup_keywordLook up a keyword or rule. Returns the official definition, a plain English explanation, examples, and which game modes it applies to.
"What does Devastating Wounds do?"
"Explain the Feel No Pain keyword"
Parameters: keyword (required), game_mode (optional)
lookup_phaseLook up a game phase by name. Returns step-by-step instructions and tips.
"Walk me through the Shooting phase"
"How does the Firefight phase work in Kill Team?"
Parameters: phase_name (required), game_mode (optional, default: 40k)
search_unitsSearch units by name, faction, keywords, or ability text. Returns a compact list (max 10 results) with faction, points, and keywords.
"Find all Necron units under 100 points"
"Search for units with the Fly keyword" "Show me units with Deep Strike"
Parameters: query (required), faction (optional), ability (optional), max_points (optional), game_mode (optional: 40k/40k_11e (default), 40k_10e, combat_patrol, kill_team)
compare_unitsCompare 2-4 units side by side. Shows full datasheets for each unit in a single response.
"Compare Intercessors vs Tactical Marines"
"Compare the Leman Russ, Predator, and Hammerhead side by side"
Parameters: units (required, array of 2-4 unit names), game_mode (optional: 40k/40k_11e (default), 40k_10e, combat_patrol, kill_team)
game_flowShow the full turn sequence for a game mode, or highlight where you are in the turn and what comes next.
"Show me the 40K turn sequence"
"I'm in the Shooting phase — what's next?" "Show the Kill Team turn sequence"
Parameters: current_phase (optional), game_mode (optional, default: 40k)
lookup_stratagemLook up a Warhammer 40,000 stratagem by name. Returns CP cost, phase timing, target, and effect.
"What does Fire Overwatch do?"
"Show me the Command Re-roll stratagem"
Parameters: name (required), faction (optional), phase (optional), detachment (optional)
search_stratagemsSearch stratagems by name, faction, phase, or detachment. Returns a compact list (max 10).
"What stratagems can I use in the Fight phase?"
"Show me Gladius Task Force stratagems"
Parameters: query (required), faction (optional), phase (optional), detachment (optional)
lookup_detachmentLook up a detachment by name. Returns the detachment ability, available enhancements, and associated stratagems.
"Show me the Gladius Task Force detachment"
"What does the Warhost detachment do for Aeldari?"
Parameters: name (required), faction (optional), game_mode (optional: 40k/40k_11e (default), 40k_10e)
lookup_enhancementLook up a character enhancement by name. Returns points cost, detachment, and effect.
"What does Adept of the Codex do?"
"Show me Aeldari enhancements"
Parameters: name (required), faction (optional), detachment (optional), game_mode (optional: 40k/40k_11e (default), 40k_10e)
lookup_ployLook up a Kill Team ploy by name. Returns type (strategic/tactical), CP cost, timing, and effect.
"What does the Bolster ploy do in Kill Team?"
"Show me Legionaries ploys"
Parameters: name (required), faction (optional), type (optional: strategic, tactical)
wound_calculatorCalculate expected damage output for an attack profile against a target. Handles re-rolls, weapon keywords (Lethal Hits, Devastating Wounds, Sustained Hits, Torrent), invulnerable saves, and Feel No Pain.
"Calculate damage: 10 attacks, BS3+, S5 AP-1 D2 vs T4 Sv3+"
"How much damage does a lascannon do to a Leman Russ?"
Parameters: attacks, hit_skill, strength, toughness, armour_save, damage (all required); armour_penetration, invulnerable_save, feel_no_pain, reroll_hits, reroll_wounds, weapon_keywords, wounds_per_model, game_mode (all optional)
determine_primary_missionDetermine each player's Primary Mission from their Force Dispositions (11th Edition Matched Play). Each player's mission is looked up from their *opponent's* Force Disposition — in a non-mirror matchup, the two players get different missions. Returns mission names only, not full scoring/objective text.
"I picked Take and Hold, my opponent picked Purge the Foe — what are our missions?"
"What's my Primary Mission if I'm Reconnaissance and they're Priority Assets?"
Parameters: your_disposition, opponent_disposition (both required, one of: Take and Hold, Purge the Foe, Reconnaissance, Priority Assets, Disruption)
lookup_crusadeLook up Crusade content (narrative play). Returns Crusade rules, relics, battle traits, and upgrades.
"What Crusade relics can Space Marines take?"
"Show me the Crusade battle traits"
Parameters: query (required), faction (optional)
All data is embedded at build time — no network calls at runtime. Data is synced daily from BSData via GitHub Actions.
| Category | Count | Source |
|---|---|---|
| 40K unit datasheets (11th Edition, default) | 2,695 | BSData/wh40k-11e |
| 40K unit datasheets (10th Edition) | 2,666 | BSData/wh40k-10e |
| Kill Team operatives | 519 | BSData/wh40k-killteam |
| Detachments (11th / 10th Edition) | 259 / 208 | BSData (auto-extracted) |
| Enhancements (11th / 10th Edition) | 895 / 827 | BSData (auto-extracted) |
| Stratagems | 1,316 | Hand-curated (Core Rules + detachment-specific per faction) |
| Kill Team ploys | 14 | Hand-curated (universal + popular factions) |
| Shared rules (11th / 10th Edition) | 35 / 33 | BSData |
| Shared rules (Kill Team) | 22 | BSData |
| Curated keywords | 25 | Hand-written, plain English, 11th Edition Core Rules |
| Game mode sequences | 3 | Hand-curated (40K, Combat Patrol, Kill Team) |
| Force Disposition mission matchups | 15 | Hand-curated (5 dispositions, full grid) |
40k / 40k_11e, default) — full-scale battles, 11th Edition rules40k_10e) — full-scale battles, 10th Edition rules (permanently supported)combat_patrol) — smaller, starter-friendly formatkill_team) — squad-level skirmish game10th Edition support isn't going away when a newer edition is added — every game_mode value, once added, keeps working.
npm install
npm run build npm test
To refresh unit data from BSData:
npm run fetch-data
npm run build
MIT (for the MCP server code).
Unit data sourced from the BSData community project — wh40k-10e, wh40k-11e, and wh40k-killteam. Game rules and army rules are the intellectual property of Games Workshop. This tool provides reference data for personal use during gameplay.