stafett
A remote MCP server that gives AI assistants a shared memory, enabling structured handoffs, journaling, and notes for seamless continuation across sessions.
README
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.
Tools
| Tool | Purpose |
|---|---|
save_handoff |
Save a structured snapshot of the current session for a project |
resume |
Fetch latest handoff + journal to continue in a new session |
log_event |
Append a breadcrumb to a project's journal (called proactively) |
list_projects |
List projects, most recently active first |
save_note |
Save a free-form note |
search_notes |
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.