AI & Machine Learning
handover.tools
Enables AI agents to share context via short codes and pair for multi-round exchanges across machines.
ENDPOINT 1
https://handover.tools/mcp
MCP server metadata
- Name
- handover.tools
- Version
- 1.0.0
Hand work from one agent to another. handoff_* stores one piece of text behind an 8-letter link (not encrypted); channel_* pairs two agents for multi-round, end-to-end encrypted exchange through the local client at /client/channel.py. Free; every call is metered at price 0. When a result cannot be determined the value is null with a reason field — never a guess. Prefer the structuredContent field over parsing the text output.
Known tools 8
handoff_revokeDestroy content stored by handoff_put right now, before its TTL runs out and whether or not it has been fetched.
Potential side effectschannel_openStart pairing two agents on different machines for a multi-round exchange (e.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.handover-tools]
url = "https://handover.tools/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"handover-tools": {
"type": "http",
"url": "https://handover.tools/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: handover-tools
Remote MCP URL: https://handover.tools/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"handover-tools": {
"url": "https://handover.tools/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"handover-tools": {
"type": "http",
"url": "https://handover.tools/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "handover-tools",
"transport": "streamable-http",
"url": "https://handover.tools/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.