Auditable memory (memory3l)

mcpkey · package no repo

io.github.jayzht/memory3l-mcp · v0.2.0

deploy just this

Audited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.

run it

on your own machines, one way per deploy method

generated from the record, not tested yet

#!/usr/bin/env bash
# memory3l (io.github.jayzht/memory3l-mcp), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-memory3l.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 memory3l-mcp==0.2.0

[Unit]
Description=MCP server memory3l (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/memory3l
WorkingDirectory=/var/lib/mcp/memory3l
ExecStart=/opt/mcp/my-agent/bin/memory3l.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/memory3l

[Install]
WantedBy=multi-user.target

generated from the record, not tested yet

docker run --rm -p 127.0.0.1:8101:8000 -e MEMORY3L_ROOT -e MEMORY3L_DB -e MEMORY3L_ALLOW_WRITE ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx memory3l-mcp==0.2.0'

generated from the record, not tested yet

# Generated by Hub for toolset "my-agent" (2026-10-18T01:50:46+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:
  memory3l:
    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 memory3l-mcp==0.2.0
    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:
      MEMORY3L_ROOT: ${MEMORY3L_ROOT}
      MEMORY3L_DB: ${MEMORY3L_DB}
      MEMORY3L_ALLOW_WRITE: ${MEMORY3L_ALLOW_WRITE}
volumes:
  npm-cache: {}
  uv-cache: {}

generated from the record, not tested yet

# Generated by Hub for toolset "my-agent" (2026-10-18T01:50:46+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: memory3l
  namespace: mcp
  labels: &id001
    app: memory3l
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: memory3l
        image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: MEMORY3L_ROOT
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MEMORY3L_ROOT
        - name: MEMORY3L_DB
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MEMORY3L_DB
        - name: MEMORY3L_ALLOW_WRITE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: MEMORY3L_ALLOW_WRITE
        command:
        - sh
        - -c
        - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx memory3l-mcp==0.2.0
        readinessProbe:
          httpGet:
            path: /status
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: memory3l
  namespace: mcp
spec:
  selector:
    app: memory3l
  ports:
  - port: 8000
    targetPort: http
    name: http

generated from the record, not tested yet

# Generated by Hub for toolset "my-agent" (2026-10-18T01:50:46+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:
  memory3l:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: memory3l
      image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: MEMORY3L_ROOT
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MEMORY3L_ROOT
      - name: MEMORY3L_DB
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MEMORY3L_DB
      - name: MEMORY3L_ALLOW_WRITE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: MEMORY3L_ALLOW_WRITE
      command:
      - sh
      - -c
      - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx memory3l-mcp==0.2.0
      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

deploy to koyeb

The form opens with CHANGE_ME for each value you supply: MEMORY3L_ROOT, MEMORY3L_DB, MEMORY3L_ALLOW_WRITE. Fill them in before you deploy.

Clients connect to the service's https://…koyeb.app address plus /mcp.

azure

deploy to azure template

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 needs

uvx memory3l-mcp==0.2.0
# env: MEMORY3L_ROOT, MEMORY3L_DB, MEMORY3L_ALLOW_WRITE

{
  "mcpServers": {
    "memory3l": {
      "command": "uvx",
      "args": [
        "memory3l-mcp==0.2.0"
      ],
      "env": {
        "MEMORY3L_ROOT": "${MEMORY3L_ROOT}",
        "MEMORY3L_DB": "${MEMORY3L_DB}",
        "MEMORY3L_ALLOW_WRITE": "${MEMORY3L_ALLOW_WRITE}"
      }
    }
  }
}

#!/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 memory3l -e "MEMORY3L_ROOT=${MEMORY3L_ROOT}" -e "MEMORY3L_DB=${MEMORY3L_DB}" -e "MEMORY3L_ALLOW_WRITE=${MEMORY3L_ALLOW_WRITE}" -- uvx memory3l-mcp==0.2.0

{
  "mcpServers": {
    "memory3l": {
      "command": "uvx",
      "args": [
        "memory3l-mcp==0.2.0"
      ],
      "env": {
        "MEMORY3L_ROOT": "${MEMORY3L_ROOT}",
        "MEMORY3L_DB": "${MEMORY3L_DB}",
        "MEMORY3L_ALLOW_WRITE": "${MEMORY3L_ALLOW_WRITE}"
      }
    }
  }
}

{
  "servers": {
    "memory3l": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "memory3l-mcp==0.2.0"
      ],
      "env": {
        "MEMORY3L_ROOT": "${MEMORY3L_ROOT}",
        "MEMORY3L_DB": "${MEMORY3L_DB}",
        "MEMORY3L_ALLOW_WRITE": "${MEMORY3L_ALLOW_WRITE}"
      }
    }
  }
}

name: my-agent
target: local
servers:
- hub: io.github.jayzht/memory3l-mcp

trust flag: no_repo
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.