MCP Hub
Back to servers

handoff-mcp

Shared memory hub for LLMs to persist and share project context, enabling seamless handoffs between different AI agents.

glama
Stars
1
Updated
Apr 27, 2026
Validated
Apr 28, 2026

handoff-mcp

MCP server that acts as a shared memory hub across multiple LLMs (Claude, Gemini, Copilot, Codex). Any agent entering a project immediately understands its architecture, patterns, and decisions — and can pick up exactly where the previous LLM left off.

Tools

ToolDescription
create_or_get_projectInitialize or retrieve a project
save_architectureSave architecture overview and tech stack
get_project_summaryFull project overview — perfect as first call
save_context_snapshotSave working state before handing off
get_context_snapshotRetrieve what the previous LLM was doing
list_sessionsList all saved sessions
save_code_patternSave reusable code patterns (JWT, FCM, etc.)
get_code_patternsRetrieve patterns by category/language
save_architectural_decisionSave an ADR (why a decision was made)
get_decisionsRetrieve architectural decisions
search_contextSearch across patterns, decisions, and snapshots

Install

Requirements: Bun

git clone https://github.com/Juan-Severiano/handoff-mcp
cd handoff-mcp
bun install

Configure

Replace /path/to/handoff-mcp with the absolute path where you cloned the repo.

Claude Desktop

File: ~/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.ts

Gemini CLI

File: ~/.gemini/settings.json

{
  "mcpServers": {
    "handoff-mcp": {
      "command": "bun",
      "args": ["/path/to/handoff-mcp/src/index.ts"]
    }
  }
}

GitHub Copilot (VS Code)

File: .vscode/mcp.json in your workspace, or VS Code user settings.json:

{
  "servers": {
    "handoff-mcp": {
      "type": "stdio",
      "command": "bun",
      "args": ["/path/to/handoff-mcp/src/index.ts"]
    }
  }
}

OpenAI Codex CLI

File: ~/.codex/config.yaml

mcpServers:
  handoff-mcp:
    command: bun
    args:
      - /path/to/handoff-mcp/src/index.ts

DB path (optional)

By default, context.db is created in the working directory. Override via env var:

{
  "mcpServers": {
    "handoff-mcp": {
      "command": "bun",
      "args": ["/path/to/handoff-mcp/src/index.ts"],
      "env": { "DB_PATH": "/your/shared/path/context.db" }
    }
  }
}

Tip: point all LLMs to the same DB_PATH so they share one database across tools.

Flow

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...

Dev

bun run dev      # watch mode
bun run inspect  # MCP Inspector
bun run build    # compile to dist/

Reviews

No reviews yet

Sign in to write a review