MCP server for managing AI session handoffs and next steps
MCP server for managing AI session handoffs and next steps
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| list_templates | List available templates for next steps, working sessions, and handoffs |
| create_project | Create a new project for tracking AI session handoffs |
| delete_project | Delete a project and all its data |
| create_next_step | Create a new next step in a project |
| start_working_session | Start working on a next step |
| create_handoff | Complete a working session with handoff details |
| get_latest_next_steps | Get open next steps ordered by priority |
| get_next_step_history | Get complete history of a next step including session and handoff |
{
"mcpServers": {
"project-handoffs": {
"command": "/opt/homebrew/bin/node",
"args": [
"/path/to/project-handoffs/build/index.js"
],
"alwaysAllow": []
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Daily Scandinavian AI benchmark — Norwegian, Swedish, Danish. 12+ models tested.
Cryptographic identity, SIGIL naming, heartbeat, and passports for AI agents.
This is part of the MCP track for the Hackathon (with a smidge of Agents)
VectorCode exposes local repository indexing and semantic code retrieval through a Python MCP server with explicit project roots.