stafett
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., "@stafettsave a handoff for the website redesign"
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.
stafett ๐โโ๏ธ
Swedish for "relay race" โ because that's what it does: passes the baton between AI assistants.
A remote MCP server that gives all your AI assistants (Claude, ChatGPT, โฆ) one shared memory. Work on something in one assistant, run out of tokens, open another one and say "continue where we left off" โ and it actually can.
The problem
AI assistants don't share anything with each other. If you use multiple accounts or providers, every switch means re-explaining everything. An MCP server can't read your chat history โ but it can give the assistant tools to save and restore working state. stafett makes that ergonomic:
Handoffs โ before switching, ask the assistant to "save a handoff": a structured snapshot (summary, decisions, next steps, open questions, snippets).
Journal โ sessions often die abruptly (token limits), too late for a handoff. The tool descriptions therefore instruct assistants to proactively log breadcrumb events during work, so there is always something to resume from.
Notes โ free-form shared memory for ideas, links and reminders.
Related MCP server: memory-bank-mcp
Tools
Tool | Purpose |
| Save a structured snapshot of the current session for a project |
| Fetch latest handoff + journal to continue in a new session |
| Append a breadcrumb to a project's journal (called proactively) |
| List projects, most recently active first |
| Save a free-form note |
| Keyword search across notes |
Stack
TypeScript ยท official MCP SDK (stateless Streamable HTTP) ยท Express ยท Upstash Redis ยท deployed on Vercel.
Auth is a secret URL: the server only answers on /mcp/<long-random-token>. Claude and ChatGPT custom connectors support OAuth or no auth โ a secret URL is the pragmatic middle ground for a personal server. Treat the URL as a password, and don't store anything sensitive.
Run locally
npm install
cp .env.example .env # set MCP_SECRET (openssl rand -hex 32); Upstash optional locally
npm run dev # http://localhost:3000/mcp/<MCP_SECRET>Without Upstash credentials the server uses in-memory storage โ fine for local testing, useless in production.
Deploy
Create a free Redis database at Upstash (or via Vercel Marketplace).
npx vercelโ set env varsMCP_SECRET,UPSTASH_REDIS_REST_URL,UPSTASH_REDIS_REST_TOKEN.Your connector URL is
https://<your-app>.vercel.app/mcp/<MCP_SECRET>.
Add to your assistants
Claude (claude.ai / Desktop): Settings โ Connectors โ Add custom connector โ paste the URL. No auth.
ChatGPT: Settings โ Connectors (requires developer mode) โ Create โ paste the URL. No auth.
Claude Code:
claude mcp add --transport http stafett <url>
Add the same URL everywhere โ that's the whole point.
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 Connectors
An MCP memory server. One memory your agents share โ across models, devices and apps.
Persistent, portable memory for AI assistants โ your private memory graph, from any MCP client.
- EngramOAuthapp.getengram
Persistent, verbatim, searchable memory for AI assistants โ one memory across every MCP client.
Persistent personal memory for AI assistants โ save, search, and recall across every MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that provides AI assistants with a shared, persistent SQLite-backed memory for storing and retrieving project context, decisions, and discoveries. It enables cross-session continuity and team-wide knowledge sharing to keep AI coding tools aligned and informed.3MIT
- AlicenseBqualityCmaintenanceAn MCP server that gives AI assistants persistent memory across sessions. It stores project context, decisions, and progress in structured markdown files as well as a knowledge graph and sequential thinking for better memory storage.36291MIT
- AlicenseAqualityAmaintenanceA local MCP server that gives AI assistants a long-term memory by capturing sessions verbatim and surfacing relevant context automatically.15872MIT
- FlicenseNot gradedqualityDmaintenanceA MCP server that provides persistent memory for AI assistants, storing personal information, relationships, and observations to enable personalized and contextual conversations.4-