rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Audit, reschedule and author Microsoft Project schedules. No Java, no Project install.
Texto original del autor
Skills que enseñan a la IA este tipo de trabajo; funcionan junto a este
Reverse engineer anything with agents, from app behavior down to native binaries.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Las listas se ordenan por una puntuación de uso (sobre 100) con estas partes
| Popularidad | 12/80 | Estrellas de GitHub o descargas semanales: la mayor cuenta 60, la menor 20 |
|---|---|---|
| Actualidad | 12/12 | Puntuación completa con una versión o cambio de código en 30 días |
| Sigue respondiendo | 0/8 | El endpoint en la nube respondió en la última revisión |
| Puntuación de uso | 24/100 |
Calidad: Pasó 3/3 revisiones básicas (se muestra, no ordena) · Impulso: Sin datos aún (Solo se usa en la pestaña En auge)
Elige la app de IA que usas y copia la configuración.
Pasó 3/3 revisiones · Funciona en tu computadora
Primero: ¿qué IA usas?
Elige tu app y los pasos aparecen abajo.
Funciona con Claude, pero hay que preparar algo antes
Sin clave y sin instalar nada · Solo en la app de Claude para computadora (Windows o Mac), no en la web ni en el móvil
SettingsDeveloperEdit Config
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Usa Microsoft Project y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Claude dice que está usando Microsoft Project o muestra una herramienta de Microsoft Project en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Anthropic el 11 nov 2026 · tu pantalla puede variar un poco según la versión
ChatGPT todavía no puede conectar Microsoft Project
Microsoft Project se instala en tu computadora, pero ChatGPT solo conecta servidores que funcionan en la web
A · Usa una app que pueda conectar Microsoft Project
B · Otros en Herramientas para desarrolladores que funcionan con ChatGPT
Elegidos entre los más usados de la misma categoría, solo los que se conectan con una dirección y sin clave
Funciona con Claude Code, pero hay que preparar algo antes
Sin clave y sin instalar nada
Mac: pulsa Command+Espacio y escribe Terminal · Windows: abre PowerShell
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Deberías ver Microsoft Project en la lista como conectado
Usa Microsoft Project y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Claude Code dice que está usando Microsoft Project o muestra una herramienta de Microsoft Project en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Anthropic el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Funciona con Cursor, pero hay que preparar algo antes
Sin clave y sin instalar nada
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Usa Microsoft Project y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Cursor dice que está usando Microsoft Project o muestra una herramienta de Microsoft Project en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Cursor el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Funciona con VS Code, pero hay que preparar algo antes
Sin clave y sin instalar nada
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Usa Microsoft Project y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si VS Code dice que está usando Microsoft Project o muestra una herramienta de Microsoft Project en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de VS Code el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Otras apps que usan MCP, como Windsurf, Zed o Gemini CLI, añaden servidores de forma distinta. Míralo en la lista de apps
Ver todas las apps que usan MCP →
La configuración JSON está en “Para desarrolladores”, abajo
Claude Code
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Claude Desktop (claude_desktop_config.json)
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Cursor (~/.cursor/mcp.json)
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
VS Code (mcp.json)
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
nuget: HorizunMsProjectMcpSegún cómo se conecta este servidor y la documentación de cada app, comprobado el 10 nov 2026.
Se ejecutan en tu computadora en
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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 20 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub HorizunGroup, dueña del repo
Último cambio de código: hace 3 días
Usa MIT
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
No revisado: solo se pueden revisar paquetes npm y PyPI con versión
Si lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.
[](https://mcp.popnx.com/en/servers/horizungroup-horizun-msproject-mcp)Pregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.
Aún no hay reseñas
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 3 de 3 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 hace 3 días, y la última versión (1.6.1) llegó al registro hace 31 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas .NET en tu computadora.
En la misma categoría: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
Misma categoría, otros creadores, comandos ya revisados. Primero los oficiales, luego por estrellas.
Cómo leer una tarjeta:↓ Descargas por semanai★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Cloudflare MCP servers
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| Este Microsoft Project | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| Dónde se ejecuta | Se instala en tu equipo | Funciona en la nube, sin instalar nada | Funciona en la nube, sin instalar nada | Funciona en la nube, sin instalar nada | Funciona en la nube, sin instalar nada | En la nube o instalado en tu equipo |
| Necesita clave | No | No | No | No | No | No |
| Se añade con + en Claude | No | No | No | Sí | No | No |
| Revisiones básicas | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| Licencia | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| Precio | Sin coste en el registro | Sin coste en el registro | Sin coste en el registro | Sin coste en el registro | Sin coste en el registro | Sin coste en el registro |
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.
An MCP server for Microsoft Project that needs neither Java nor Microsoft Project — and tells you the truth about what it wrote.
It works as a PMO, not as a software operator. It does not just click through Microsoft Project on your behalf: it plans, controls and reports the way a project management office does, following PMBOK — a WBS that obeys the 100% rule, a cost-loaded baseline, earned value and earned schedule, quantitative schedule risk, formal change control with reasons and approvers, weekly look-ahead planning with PPC, and a period status report with its trend. Project is the engine; the method is the product.
*Español*
Point any MCP client at a .mpp, a Primavera .xer, or an MSPDI .xml and ask real questions: where the critical path runs, which resources are overbooked, whether the schedule would survive a DCMA audit, what a two-week slip actually does to the finish date. Then write changes back — and know which ones landed, because every one is re-read from the model before it is reported.
dotnet tool install -g HorizunMsProjectMcp
That is the whole install. No JVM. No Microsoft Project. No licence. It reads and schedules on its own.
| Client | Do this |
|---|---|
| Claude Desktop | Download the .mcpb from Releases and drop it on Settings → Extensions. It installs the server itself — nothing to run first. |
| Claude Code | claude mcp add horizun-msproject-mcp -- horizun-msproject-mcp |
| Codex | codex mcp add horizun-msproject-mcp -- horizun-msproject-mcp |
| ChatGPT | Needs an HTTPS bridge in front of the stdio server. How, and what to weigh first. |
Full per-client instructions, including the plugin route and uninstall, are in docs/INSTALL.md.
There are a handful of Microsoft Project MCP servers. Every one of them requires Java, or a licensed Microsoft Project install, or a paid JDBC driver — and on the machine this was built on, none of them would start. Eight things here are not available anywhere else:
| Zero prerequisites | A single .NET binary. MPXJ is compiled to .NET through IKVM, so there is no JVM anywhere in the picture, and no Microsoft Project either. |
| Microsoft Project's dates, not an imitation | Where Project is installed, Project itself calculates every date this server reports. On seven real schedules — 8,823 tasks — recalculations and edits made through it matched Project on every task, to the minute. How. |
| Verified writes | Microsoft Project silently ignores writes all the time — auto-scheduled dates, hard constraints, summary rollups, calculated costs. Nothing here is reported as applied until it has been read back out of the model and matched. |
| DCMA 14-point assessment | The industry standard for judging whether a schedule can be run on. The Primavera servers implement it; none of the Microsoft Project ones do. Check 12 genuinely injects a 600-day delay and measures what moves. |
| It recovers logic nobody linked | A schedule laid out correctly on the bar chart but never linked is the most common defect there is: DCMA flags it, nothing fixes it. The dates already state the order — this reads it back out, verifies the same order holds across every repetition, and proposes the missing links. |
| Reprogramming that is measured | Recovery options are applied to a copy of the schedule, rescheduled, and reported with the finish date they actually produce. An option that recovers nothing says so instead of being offered as advice. |
| It learns from your past projects | Point it at finished schedules and it reports what each activity really took and what usually precedes it, then drafts a new programme from that — one task per unit, sequenced the way the trades actually followed each other. |
| A BIM bridge | Tie schedule tasks to model elements by code, turn measured quantities into duration proposals, and emit the per-element dates that drive 4D in Navisworks and the progress dashboard in Power BI. Nobody else does this at all. |
Session — project_health · project_open · project_save
project_health is a doctor, not a ping. It detects Microsoft Project, tests whether its COM server *actually starts*, and when it does not, hands back the HRESULT diagnosis and the repair steps. That is not hypothetical: this machine hit CO_E_SERVER_EXEC_FAILURE with a perfectly valid registration, and step one of the repair path it emits is what fixed it.
Reading — project_info · tasks_query · links_query · resources_query · timephased_query
Filtered, paged, field-selectable. Tasks are addressed by their stable uid; the row id is display only, because it shifts the moment a task is inserted and addressing by it edits the wrong task.
Analysis — schedule_analyze · schedule_qa · baseline_compare
Computed server-side, so the agent asks a question instead of pulling two thousand tasks into context. Critical path, float distribution, driving path, day-by-day overallocation, DCMA-14, and full earned value (BCWS/BCWP/ACWP, SPI, CPI, EAC, TCPI) — denominated in cost where the schedule carries costs, in work hours where it carries hours, and weighted by duration where it carries neither, which is most of them. The report says which.
Writing — tasks_write · links_write · resources_write · calendars_write · schedule_update
Batched, typed, verified. Cycles are refused before they are applied, with the offending chain named. Calendars are edited in full: the working week and its hours (half or full Saturdays, shifts), working and non-working exceptions with their hours, the project calendar, and task and resource calendars. Tasks take their type, effort-driven flag, fixed cost, a baseline cost that leaves the baseline dates alone, and a whole outline in one batch; resources take rates, overtime rates, material units and max units Project actually sees. schedule_update op level_resources levels with Microsoft Project's own leveller, optionally within slack only. One thing is not offered: moving a task to another position in the outline. Asking for it gets a refusal that names it — an operation that half-works is worse than one that is absent.
Planning — schedule_recovery · schedule_scenarios · schedule_target · schedule_sequence · schedule_learn · schedule_generate
Reprogramming, measured rather than asserted. schedule_recovery finds what is late, ranks it by how much of the schedule sits behind it, then tries each recovery lever — removing lag on the driving chain, overlapping hand-offs once half the predecessor is done, compressing the longest critical tasks, working full Saturdays, and all of them together — on a throwaway copy and reports the finish date each one genuinely produces, and why any lever was dropped. schedule_scenarios compares alternatives you define — calendar, resource, task and logic changes together — side by side: finish, cost, overallocation, critical tasks, nothing committed. schedule_target tests a date you have been handed and names the work the network does not hold in place. schedule_sequence recovers the logic a schedule is missing by reading the order its own dates already state — the planner laid the work out correctly and never linked it, and that decision is recoverable. schedule_learn mines finished schedules for how long each activity actually takes and what usually comes before it; schedule_generate turns that into a first draft, one task per apartment or floor, sequenced the way the history says the trades follow each other.
Feed schedule_learn a model export alongside the schedules and it measures productivity — what a crew actually got through in a day — by joining quantities to tasks on the shared code. schedule_generate then sizes durations from the quantities of the new project rather than copying a remembered duration, because the rate is what carries between projects and the quantity is what changes. Give one export per schedule, in the same order: rates are measured per project, and quantities totalled across projects would inflate every one of them.
A draft can only be as well sequenced as the schedules it learned from. Where the sources link each activity to itself unit after unit but never to the trades around it, both tools say so and name the number: the library reports how many activities learned a predecessor other than themselves, and the draft reports how many trades it left with nothing scheduled before them.
Project control — schedule_risk, plus PMO aspects of the tools above
schedule_risk): Monte Carlo over the network's own logic, all four link types and lags, with three-point ranges per task or a default spread, counted in working hours of the project calendar (half Saturdays and elapsed lags included) and anchored on the schedule's own finish, so the most-likely run is the schedule. P10/P50/P80/P90 finish, probability of a target and of the baseline, P80 contingency, risk drivers by criticality and sensitivity. Seeded runs repeat exactly.schedule_analyze aspect status_report): planned vs earned, SPI, CPI, earned-schedule SPI(t), EAC by three methods, TCPI, forecast finish, milestones at risk, top issues, and the trend of every recorded cut-off.schedule_update op load_budget): a budget by code, the same code BIM links on, spread over the tasks as cost; lines no task carries are reported. timephased_query measure s_curve returns cumulative PV, EV and AC, in money when costs are loaded.reason (and takes approvedBy); every baseline, budget load and committed edit batch is logged with its finish impact (aspect change_log).lookahead): the next weeks' work with each task's constraints, ready vs constrained, and PPC against last week's recorded commitment (Last Planner).schedule_qa checks the 100% rule (empty summaries, cost or resources on summaries, duplicate WBS codes, single-child summaries); project_export format wbs_dictionary writes the WBS dictionary.The history (cut-offs, commitments, changes) lives beside the schedule in .hzpmo.json, so it survives whichever tool writes the .mpp next.
Interop — project_export · project_import · bim_link · bim_sync
CSV, JSON, MSPDI, Primavera XER and PMXML, native .mpp, and a shaped Power BI dataset. Imports plan before they write.
The 27 tools present about 13,500 tokens of schema, in every prompt, for as long as the server is connected. That is the honest price of the surface and it is worth knowing before choosing to carry it. It is also why the surface stays near 25: the largest alternative ships 79 tools, and past a point an agent cannot hold the surface in its head well enough to choose correctly within it.
Nothing is applied until it is verified.
{