On Board
mcpkey · packageio.github.swisspra/On_Board · v4.0.4
Cross-platform shared memory and ticket coordination for AI agents across MCP clients.
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
#!/usr/bin/env bash # on-board (io.github.swisspra/On_Board), recipe baremetal (generated). # Generated by Hub for toolset "my-agent"; started by mcp-my-agent-on-board.service. set -euo pipefail export HOST=127.0.0.1 PORT=8101 exec uvx mcp-proxy --host 127.0.0.1 --port 8101 --pass-environment -- uvx onboard-memory-mcp==4.0.4 [Unit] Description=MCP server on-board (toolset my-agent), generated by Hub After=network-online.target Wants=network-online.target [Service] Type=simple User=mcp Group=mcp EnvironmentFile=/etc/mcp/my-agent.env Environment=HOME=/var/lib/mcp/on-board WorkingDirectory=/var/lib/mcp/on-board ExecStart=/opt/mcp/my-agent/bin/on-board.sh Restart=on-failure RestartSec=5 NoNewPrivileges=true ProtectSystem=strict ProtectHome=true PrivateTmp=true ReadWritePaths=/var/lib/mcp/on-board [Install] WantedBy=multi-user.target
generated from the record, not tested yet
docker run --rm -p 127.0.0.1:8101:8000 -e AGENT_PROJECT_DIR ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx onboard-memory-mcp==4.0.4'
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T04:36:59+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
on-board:
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
command:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx onboard-memory-mcp==4.0.4
ports:
- 127.0.0.1:8101:8000
volumes:
- uv-cache:/root/.cache/uv
healthcheck:
test:
- CMD
- python3
- -c
- import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/status')
interval: 30s
timeout: 5s
retries: 5
start_period: 2m
restart: unless-stopped
environment:
AGENT_PROJECT_DIR: ${AGENT_PROJECT_DIR}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T04:36:59+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: on-board
namespace: mcp
labels: &id001
app: on-board
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: on-board
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
ports:
- containerPort: 8000
name: http
env:
- name: AGENT_PROJECT_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AGENT_PROJECT_DIR
command:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx onboard-memory-mcp==4.0.4
readinessProbe:
httpGet:
path: /status
port: http
initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
name: on-board
namespace: mcp
spec:
selector:
app: on-board
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T04:36:59+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
on-board:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: on-board
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
ports:
- containerPort: 8000
name: http
env:
- name: AGENT_PROJECT_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AGENT_PROJECT_DIR
command:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx onboard-memory-mcp==4.0.4
readinessProbe:
httpGet:
path: /status
port: http
initialDelaySeconds: 10
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
The form opens with CHANGE_ME for each value you supply: AGENT_PROJECT_DIR. Fill them in before you deploy.
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The portal asks for each value you supply as a secure parameter; the deployment's outputs list the endpoints.
connect to it
copy what your client needsuvx onboard-memory-mcp==4.0.4 # env: AGENT_PROJECT_DIR
{
"mcpServers": {
"on-board": {
"command": "uvx",
"args": [
"onboard-memory-mcp==4.0.4"
],
"env": {
"AGENT_PROJECT_DIR": "${AGENT_PROJECT_DIR}"
}
}
}
}
#!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add on-board -e "AGENT_PROJECT_DIR=${AGENT_PROJECT_DIR}" -- uvx onboard-memory-mcp==4.0.4
{
"mcpServers": {
"on-board": {
"command": "uvx",
"args": [
"onboard-memory-mcp==4.0.4"
],
"env": {
"AGENT_PROJECT_DIR": "${AGENT_PROJECT_DIR}"
}
}
}
}
{
"servers": {
"on-board": {
"type": "stdio",
"command": "uvx",
"args": [
"onboard-memory-mcp==4.0.4"
],
"env": {
"AGENT_PROJECT_DIR": "${AGENT_PROJECT_DIR}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.swisspra/On_Board
- not probed yet: tools unpinned, ingest lists them
tools
Not probed yetThe tools appear once the hub or its worker has listed this entry. Running it still works: your client lists them on first start.