Handoff runs on your own machine — the client starts it, so there is no endpoint to ping. 75 installs a week from pypi. Last commit 11 Jul 2026.
Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add handoff-mcp -- uvx handoff-mcp
{
"mcpServers": {
"handoff-mcp": {
"args": [
"handoff-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.handoff-mcp]
command = "uvx"
args = ["handoff-mcp"]
{
"mcpServers": {
"handoff-mcp": {
"args": [
"handoff-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"handoff-mcp": {
"args": [
"handoff-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
HANDOFF_VAULT (Path to the shared markdown vault (one vault across all projects).), HANDOFF_PROJECT (Project namespace for this agent/repo within the shared vault.).
The author declared them in the registry entry; get the values from the project itself.
Cross-session memory for Claude Code — context capture, semantic search, recall
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled.
Local memory for Claude Code. Semantic recall across session history with zero API calls.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Answers built from our own checks of this server.