Big Brain
mcpkey · packageio.github.jzhao234/big-brain · v0.3.2
Plain-markdown second brain for you and your AI: notes, projects, tasks, search, links.
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
# once, as root:
# as_mcp DIR COMMAND...: runs COMMAND as the mcp user in DIR, its home, sandboxed as the
# units are: a package's install scripts can write to DIR only, as the server later can
as_mcp() {
local dir="$1"; shift
systemd-run --quiet --wait --pipe --collect --uid=mcp --gid=mcp \
-p WorkingDirectory="$dir" -p Environment=HOME="$dir" -p ReadWritePaths="$dir" \
-p NoNewPrivileges=true -p ProtectSystem=strict -p ProtectHome=true -p PrivateTmp=true \
-- "$@" </dev/null
}
install -d -m 0750 -o mcp -g mcp /var/lib/mcp/big-brain
# big-brain: its packages, installed whole before its unit starts (no session installs)
# npx takes a half-installed tree for installed: a rerun starts them afresh
systemctl stop mcp-my-agent-big-brain.service 2>/dev/null || true
as_mcp /var/lib/mcp/big-brain rm -rf /var/lib/mcp/big-brain/.npm/_npx
as_mcp /var/lib/mcp/big-brain npx --yes --package=@jzhao234/[email protected] -- true
as_mcp /var/lib/mcp/big-brain npx --yes --package=supergateway@4 -- true
#!/usr/bin/env bash
# big-brain (io.github.jzhao234/big-brain), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-big-brain.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec npx -y supergateway@4 --stdio 'npx -y @jzhao234/[email protected]' --outputTransport streamableHttp --stateful --host 127.0.0.1 --port 8101 --streamableHttpPath /mcp --healthEndpoint /healthz
[Unit]
Description=MCP server big-brain (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/big-brain
WorkingDirectory=/var/lib/mcp/big-brain
ExecStart=/opt/mcp/my-agent/bin/big-brain.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/big-brain
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
docker run --rm -p 127.0.0.1:8101:8000 -e BIG_BRAIN_VAULT node:22-alpine sh -c 'npx -y supergateway@4 --stdio '"'"'npx -y @jzhao234/[email protected]'"'"' --outputTransport streamableHttp --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz'
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:48:42+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:
big-brain:
image: node:22-alpine
command:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y @jzhao234/[email protected]' --outputTransport streamableHttp
--stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
ports:
- 127.0.0.1:8101:8000
volumes:
- npm-cache:/root/.npm
healthcheck:
test:
- CMD-SHELL
- wget -qO- http://127.0.0.1:8000/healthz || exit 1
interval: 30s
timeout: 5s
retries: 5
start_period: 2m
restart: unless-stopped
environment:
BIG_BRAIN_VAULT: ${BIG_BRAIN_VAULT}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:48:42+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: big-brain
namespace: mcp
labels: &id001
app: big-brain
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: big-brain
image: node:22-alpine
ports:
- containerPort: 8000
name: http
env:
- name: BIG_BRAIN_VAULT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BIG_BRAIN_VAULT
args:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y @jzhao234/[email protected]' --outputTransport streamableHttp
--stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
readinessProbe:
httpGet:
path: /healthz
port: http
initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
name: big-brain
namespace: mcp
spec:
selector:
app: big-brain
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:48:42+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:
big-brain:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: big-brain
image: node:22-alpine
ports:
- containerPort: 8000
name: http
env:
- name: BIG_BRAIN_VAULT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BIG_BRAIN_VAULT
args:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y @jzhao234/[email protected]' --outputTransport streamableHttp
--stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
readinessProbe:
httpGet:
path: /healthz
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: BIG_BRAIN_VAULT. 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 needsnpx -y @jzhao234/[email protected] # env: BIG_BRAIN_VAULT
{
"mcpServers": {
"big-brain": {
"command": "npx",
"args": [
"-y",
"@jzhao234/[email protected]"
],
"env": {
"BIG_BRAIN_VAULT": "${BIG_BRAIN_VAULT}"
}
}
}
}
#!/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 big-brain -e "BIG_BRAIN_VAULT=${BIG_BRAIN_VAULT}" -- npx -y @jzhao234/[email protected]
{
"mcpServers": {
"big-brain": {
"command": "npx",
"args": [
"-y",
"@jzhao234/[email protected]"
],
"env": {
"BIG_BRAIN_VAULT": "${BIG_BRAIN_VAULT}"
}
}
}
}
{
"servers": {
"big-brain": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@jzhao234/[email protected]"
],
"env": {
"BIG_BRAIN_VAULT": "${BIG_BRAIN_VAULT}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.jzhao234/big-brain
- not probed yet: tools unpinned, ingest lists them
tools
Probe result: needs authdocker: credentials=placeholder: no MCP server found (:8000/mcp: HTTP 404: MCPError: MCP server process failed; :8000/: HTTP 404: MCPError: Not Found) …(creates it if missing) tasks [options] list open tasks (due-date order) task add, update, or complete tasks projects [options] list projects project create projects, change status links <ref...> show a note's outgoing links and backlinks tags list tags with usage counts doctor [options] lint the vault (broken links, stale projects, overdue tasks…) install-skills [options] install the brain/capture/weekly skills into Claude Code (~/.claude/skills) setup [options] [dir] one-step setup: install, create or adopt a vault (default ~/brain), connect Claude Code and Codex agents install or save each coding agent's setup (skills, instructions, hooks, status line) mcp run the MCP server over stdio (same as big-brain-mcp) mcp-http [options] run the authenticated Streamable HTTP MCP server help [command] display help for command [supergateway] Child exited: code=1, signal=null; baremetal: same crash as docker
runs · 1
the latest tests of this entry by the hub and its workers, newest first| date | worker | method | status | sandbox | reason |
|---|---|---|---|---|---|
| 2026-10-18 18:02 | local-mac-vm | docker | needs auth | gvisor | docker: credentials=placeholder: no MCP server found (:8000/mcp: HTTP 404: MCPError: MCP server process failed; :8000/: HTTP 404: MCPError: Not Found) …(creates… |