Productivity · Local MCP server
On Board
Cross-platform shared memory and ticket coordination for AI agents across MCP clients.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.swisspra/On_Board- Version
- 4.0.4
- Status
- Active
- Category
- productivity
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-08-03
- Updated
- 2026-08-03
- Publisher
- swisspra (GitHub) · 2 servers with pages here
- Website
- swisspra.github.io/On_Board/
- Repository
- github.com/swisspra/On_Board
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | onboard-memory-mcp | 4.0.4 | stdio |
How to connect On Board
On Board runs locally from a Python package published to PyPI: onboard-memory-mcp version 4.0.4. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx onboard-memory-mcp. It reads the environment variable AGENT_PROJECT_DIR (required); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"on_board": {
"command": "uvx",
"args": [
"onboard-memory-mcp"
],
"env": {
"AGENT_PROJECT_DIR": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from swisspra (GitHub)
| Server | Runs |
|---|---|
| PursersCoordinate AI-agent work on a local-first, owner-controlled MCP board. | Local · HTTP, stdio |
More productivity servers
| Server | Runs |
|---|---|
| OmnierTurn signals from email, CRM, and meetings into a prioritized daily sales to-do list. | Remote · HTTP |
| OmniFocusFull CRUD MCP server for OmniFocus via Omni Automation — tasks, projects, folders, tags, recurrence. | Local · stdio |
| OmniSignalLive market intelligence & AI content strategy: trends, competitor moves, content calendar. | Remote · HTTP |
| omp-worker-mcpDelegate complete coding tasks to the local OMP default model and inspect the result. | Local · stdio |
| OnboardYour AI copilot for customer onboarding — projects, KPIs, tasks, and safe writes. | Remote · SSE, HTTP |
| OnboardingNew-hire onboarding: role-based task templates, day-one to day-ninety checklists, completion. | Remote · HTTP |
| OneFind, document and execute authenticated API calls across 700+ apps via one MCP server. | Remote & Local · HTTP, stdio |
| One BrainShared memory for a team in Claude Code: what one person records, everyone has. | Remote · HTTP |