handoff-mcp
handoff-mcp
Servidor MCP que actúa como un centro de memoria compartida entre múltiples LLM (Claude, Gemini, Copilot, Codex). Cualquier agente que entra en un proyecto comprende inmediatamente su arquitectura, patrones y decisiones, y puede continuar exactamente donde lo dejó el LLM anterior.
Herramientas
Herramienta | Descripción |
| Inicializar o recuperar un proyecto |
| Guardar la visión general de la arquitectura y la pila tecnológica |
| Resumen completo del proyecto: perfecto como primera llamada |
| Guardar el estado de trabajo antes de realizar una transferencia |
| Recuperar lo que estaba haciendo el LLM anterior |
| Listar todas las sesiones guardadas |
| Guardar patrones de código reutilizables (JWT, FCM, etc.) |
| Recuperar patrones por categoría/lenguaje |
| Guardar una ADR (por qué se tomó una decisión) |
| Recuperar decisiones arquitectónicas |
| Buscar entre patrones, decisiones y capturas de estado |
Related MCP server: ai-cortex
Instalación
Requisitos: Bun
git clone https://github.com/Juan-Severiano/handoff-mcp
cd handoff-mcp
bun installConfiguración
Reemplaza /path/to/handoff-mcp con la ruta absoluta donde clonaste el repositorio.
Claude Desktop
Archivo: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"handoff-mcp": {
"command": "bun",
"args": ["/path/to/handoff-mcp/src/index.ts"]
}
}
}Claude Code
claude mcp add handoff-mcp bun /path/to/handoff-mcp/src/index.tsGemini CLI
Archivo: ~/.gemini/settings.json
{
"mcpServers": {
"handoff-mcp": {
"command": "bun",
"args": ["/path/to/handoff-mcp/src/index.ts"]
}
}
}GitHub Copilot (VS Code)
Archivo: .vscode/mcp.json en tu espacio de trabajo, o settings.json de usuario de VS Code:
{
"servers": {
"handoff-mcp": {
"type": "stdio",
"command": "bun",
"args": ["/path/to/handoff-mcp/src/index.ts"]
}
}
}OpenAI Codex CLI
Archivo: ~/.codex/config.yaml
mcpServers:
handoff-mcp:
command: bun
args:
- /path/to/handoff-mcp/src/index.tsRuta de la base de datos (opcional)
Por defecto, context.db se crea en el directorio de trabajo. Puedes sobrescribirlo mediante una variable de entorno:
{
"mcpServers": {
"handoff-mcp": {
"command": "bun",
"args": ["/path/to/handoff-mcp/src/index.ts"],
"env": { "DB_PATH": "/your/shared/path/context.db" }
}
}
}Consejo: apunta todos los LLM a la misma
DB_PATHpara que compartan una única base de datos entre herramientas.
Flujo
Claude works on the project
→ create_or_get_project("my-app")
→ save_architecture({ description: "React Native + Spring Boot" })
Claude runs low on tokens
→ save_context_snapshot({
llmModel: "claude-opus-4",
taskDescription: "Implementing push notifications",
recentChanges: "FCM handler done",
nextSteps: "Wire up Foreground Service, test Android 16"
})
Gemini takes over
→ get_project_summary("my-app") # full context in one call
→ get_context_snapshot("my-app") # picks up exactly where Claude stopped
→ continues...Desarrollo
bun run dev # watch mode
bun run inspect # MCP Inspector
bun run build # compile to dist/This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides persistent context synchronization and memory management for AI agents across sessions and projects, including file indexing, bug tracking, spatial navigation, and agent-to-agent handoff coordination.113MIT
- AlicenseNot gradedqualityBmaintenanceProvides durable project context for coding agents, including project maps, session history, and explicit memories, all stored locally.746MIT
- AlicenseNot gradedqualityCmaintenanceGives AI agents persistent memory, handoffs, and shared context across sessions, enabling seamless continuity and multi-agent collaboration.6668Inno Setup
- AlicenseAqualityAmaintenanceShared memory and handoff hub for AI agents, enabling seamless context transfer between sessions with token-budgeted resumes and automatic handoffs.1011MIT
Related MCP Connectors
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Juan-Severiano/handoff-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server