PMOS
PMOS
Sistema operativo para product managers. Un servidor MCP que proporciona al agente datos de producto, comentarios, métricas, análisis en sandbox y tickets de Jira con aprobación — para que pueda investigar caídas, redactar PRDs y registrar trabajo con evidencia.
Implementado en OpenCode.
Qué obtienes
Herramientas
Herramienta | Propósito |
| Producto, usuarios, competidores (predeterminado: ShipIt) |
| Funcionalidades de la hoja de ruta + recuento de comentarios |
| Citas, sentimiento, temas |
| Conversión de onboarding a lo largo del tiempo |
| Series de funcionalidades (p. ej., finalización, abandono en el paso 3) |
| pandas/Python aislado (Docker; desactivado en compose) |
| Vista previa primero; |
Recursos: product://shipit · feature://{id} · metrics://onboarding
Prompts: generate_prd · analyze_feature · analyze_customer_feedback
Habilidades (.opencode/skills/): analizar comentarios, análisis de funcionalidades, redactar PRD, priorizar la hoja de ruta, crear tickets de Jira.
Related MCP server: HyperXosist Agent
Datos de demostración
Producto precargado ShipIt — SaaS de gestión de producto para ingeniería frente a Linear / Jira / Asana. El asistente de onboarding es la fuga: la finalización cae, el abandono en el paso 3 sube y los comentarios de configuración son mayoritariamente negativos.
Ejecución
cp deployment/.env.example deployment/.env # set PMOS_MCP_TOKEN
cd deployment && docker compose up --buildSalud: GET http://localhost:8000/health · MCP: http://localhost:8000/mcp
Cliente:
{
"mcpServers": {
"pmos": {
"url": "http://localhost:8000/mcp",
"headers": { "Authorization": "Bearer <PMOS_MCP_TOKEN>" }
}
}
}Jira opcional: JIRA_URL, JIRA_EMAIL, JIRA_API_TOKEN, JIRA_PROJECT en deployment/.env. Si faltan credenciales → stub local. Se necesita un proyecto real de Jira Software (no Atlas).
cd mcp && python tests/run_tests.pySQLite local si PMOS_DATABASE_URL no está definida; Postgres en Docker.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP Server for an Agent Task Marketplace
Analytics for MCP servers. Find out which of your tools agents get wrong. MCPulse shows you which tools AI agents retry, which come back empty, and which they never call at all. Two lines inside your own server. It never sees your arguments or your results. getmcpulse.com
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that exposes product-management tools for AI agents, including backlog prioritization, feedback analysis, capacity assessment, and dependency mapping.-
- AlicenseNot gradedqualityBmaintenanceMCP server for noise-reduced X (Twitter) search planning and Feedback-to-Fix engineering handoffs. Enables AI agents to generate structured search plans, filter signals, and build handoff packages via MCP tools.1MIT
- AlicenseAqualityDmaintenanceAn MCP server that reads a team's interviews, tickets, and docs to build a model of the product, exposing tools to ask questions, list contradictions and gaps, and draft documents, with all answers citing their source fragments.68 npmMIT

mcp-reviewofficial
AlicenseAqualityAmaintenanceAn MCP server for in-loop design review of web previews. It enables agents to submit a preview URL, receive structured findings with suggested fixes, and recheck after applying changes, while never editing code itself.52MIT