Allows GitHub Copilot in VS Code to read and write project context, enabling continuity across different LLM agents.
Allows OpenAI Codex CLI to share project memory, so it can resume work where other LLMs left off.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@handoff-mcp get project summary for my-app"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Tool | Description |
| Initialize or retrieve a project |
| Save architecture overview and tech stack |
| Full project overview — perfect as first call |
| Save working state before handing off |
| Retrieve what the previous LLM was doing |
| List all saved sessions |
| Save reusable code patterns (JWT, FCM, etc.) |
| Retrieve patterns by category/language |
| Save an ADR (why a decision was made) |
| Retrieve architectural decisions |
| Search across patterns, decisions, and snapshots |
Related MCP server: ai-cortex
No install needed. Just add the config below to your tool and it runs automatically via bunx.
Requires Bun installed on your machine. Install it with:
curl -fsSL https://bun.sh/install | bash
File: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"handoff-mcp": {
"command": "bunx",
"args": ["handoff-mcp"]
}
}
}claude mcp add handoff-mcp bunx handoff-mcpFile: ~/.gemini/settings.json
{
"mcpServers": {
"handoff-mcp": {
"command": "bunx",
"args": ["handoff-mcp"]
}
}
}File: .vscode/mcp.json in your workspace
{
"servers": {
"handoff-mcp": {
"type": "stdio",
"command": "bunx",
"args": ["handoff-mcp"]
}
}
}File: ~/.codex/config.yaml
mcpServers:
handoff-mcp:
command: bunx
args:
- handoff-mcpBy default each tool creates its own context.db in the working directory. To share the same memory across all LLMs, point them all to the same file:
{
"mcpServers": {
"handoff-mcp": {
"command": "bunx",
"args": ["handoff-mcp"],
"env": { "DB_PATH": "/Users/you/handoff.db" }
}
}
}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...git clone https://github.com/Juan-Severiano/handoff-mcp
cd handoff-mcp
bun install
bun run dev # watch mode
bun run inspect # MCP Inspector
bun run build # compile to dist/This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
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.
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