MOF, Dash and MCP on one server.
Linux amd64 · Docker Compose v2.20+ · 2 vCPU / 4 GB · inbound port 80
Database
Image source
Download compose.yaml
Docker Hub · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Set x-db-password once before the first start.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-db-password: &db-password "REPLACE_WITH_A_LONG_RANDOM_PASSWORD"
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
postgres:
image: postgres:16-alpine
restart: unless-stopped
logging: *logging
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: *db-password
volumes:
- pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres -d postgres"]
interval: 5s
timeout: 5s
retries: 20
mof:
image: mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
depends_on:
postgres:
condition: service_healthy
environment:
RK_POSTGRES_0_ADDR: postgres:5432
RK_POSTGRES_0_USER: postgres
RK_POSTGRES_0_PASS: *db-password
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
pgdata:
offer-cache:
mofcloud/mof:v2.0.15mofcloud/dash:v2.0.17mofcloud/mof-mcp:v2.0.3Alibaba Cloud ACR · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Set x-db-password once before the first start.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-db-password: &db-password "REPLACE_WITH_A_LONG_RANDOM_PASSWORD"
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
postgres:
image: postgres:16-alpine
restart: unless-stopped
logging: *logging
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: *db-password
volumes:
- pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres -d postgres"]
interval: 5s
timeout: 5s
retries: 20
mof:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
depends_on:
postgres:
condition: service_healthy
environment:
RK_POSTGRES_0_ADDR: postgres:5432
RK_POSTGRES_0_USER: postgres
RK_POSTGRES_0_PASS: *db-password
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
pgdata:
offer-cache:
registry.cn-hangzhou.aliyuncs.com/mofcloud/mof:v2.0.15registry.cn-hangzhou.aliyuncs.com/mofcloud/dash:v2.0.17registry.cn-hangzhou.aliyuncs.com/mofcloud/mof-mcp:v2.0.3GHCR · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Set x-db-password once before the first start.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-db-password: &db-password "REPLACE_WITH_A_LONG_RANDOM_PASSWORD"
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
postgres:
image: postgres:16-alpine
restart: unless-stopped
logging: *logging
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: *db-password
volumes:
- pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U postgres -d postgres"]
interval: 5s
timeout: 5s
retries: 20
mof:
image: ghcr.io/mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
depends_on:
postgres:
condition: service_healthy
environment:
RK_POSTGRES_0_ADDR: postgres:5432
RK_POSTGRES_0_USER: postgres
RK_POSTGRES_0_PASS: *db-password
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: ghcr.io/mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: ghcr.io/mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
pgdata:
offer-cache:
ghcr.io/mofcloud/mof:v2.0.15ghcr.io/mofcloud/dash:v2.0.17ghcr.io/mofcloud/mof-mcp:v2.0.3Keep the service names mof, mof-mcp and dash. The services find each other by these names (mof:8080, mof-mcp:8001), so nothing else needs configuring; renamed services can’t connect.
Database password
Before the first start, change this one line in compose.yaml. Keep the same password when upgrading.
x-db-password: &db-password "REPLACE_WITH_A_LONG_RANDOM_PASSWORD"Start
docker compose config --quiet
docker compose up -d
docker compose psOnce healthy, get the Admin password:
docker compose logs mof | grep "Admin password"Open MOF
http://SERVER_IP/adminInstall your license and create users.
http://SERVER_IPUsers sign in with their MOF accounts.
Connect an AI client through MCP
Enable access in Admin → Settings → MCP. Personal tokens need no OAuth. Browser-based authorization requires public HTTPS and OAuth configuration.
Private network · CREATEDB permission required · TLS-only PostgreSQL unsupported.
Download compose.yaml
Docker Hub · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Fill in the existing database address, user and password.
# Private-network PostgreSQL without TLS. TLS-only databases are not supported by this release.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
mof:
image: mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
environment:
RK_POSTGRES_0_ADDR: "db.example.com:5432"
RK_POSTGRES_0_USER: "mof"
RK_POSTGRES_0_PASS: "REPLACE_WITH_YOUR_DATABASE_PASSWORD"
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
offer-cache:
mofcloud/mof:v2.0.15mofcloud/dash:v2.0.17mofcloud/mof-mcp:v2.0.3Alibaba Cloud ACR · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Fill in the existing database address, user and password.
# Private-network PostgreSQL without TLS. TLS-only databases are not supported by this release.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
mof:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
environment:
RK_POSTGRES_0_ADDR: "db.example.com:5432"
RK_POSTGRES_0_USER: "mof"
RK_POSTGRES_0_PASS: "REPLACE_WITH_YOUR_DATABASE_PASSWORD"
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: registry.cn-hangzhou.aliyuncs.com/mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
offer-cache:
registry.cn-hangzhou.aliyuncs.com/mofcloud/mof:v2.0.15registry.cn-hangzhou.aliyuncs.com/mofcloud/dash:v2.0.17registry.cn-hangzhou.aliyuncs.com/mofcloud/mof-mcp:v2.0.3GHCR · MOF v2.0.15 · Dash v2.0.17 · MCP v2.0.3
Download compose.yaml ↓View file and images
# MOF v2.0.15 + Dash v2.0.17 + MCP v2.0.3 — Linux amd64
# Save as compose.yaml. Fill in the existing database address, user and password.
# Private-network PostgreSQL without TLS. TLS-only databases are not supported by this release.
# Keep your existing database password and volume names when upgrading.
# Keep the service names mof, mof-mcp and dash: they find each other by them (mof:8080,
# mof-mcp:8001). Renamed services can't connect.
name: mof
x-logging: &logging
driver: json-file
options:
max-size: "20m"
max-file: "5"
services:
mof:
image: ghcr.io/mofcloud/mof:v2.0.15
restart: unless-stopped
logging: *logging
environment:
RK_POSTGRES_0_ADDR: "db.example.com:5432"
RK_POSTGRES_0_USER: "mof"
RK_POSTGRES_0_PASS: "REPLACE_WITH_YOUR_DATABASE_PASSWORD"
volumes:
- offer-cache:/usr/src/mof/offer-cache
healthcheck:
test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/v1/mof/site-info"]
start_period: 60s
interval: 10s
timeout: 5s
retries: 30
mof-mcp:
image: ghcr.io/mofcloud/mof-mcp:v2.0.3
restart: unless-stopped
logging: *logging
# Private: no ports. Found by its service name, so any service can restart alone.
depends_on:
mof:
condition: service_healthy
healthcheck:
test: ["CMD", "node", "/app/build/healthcheck.js"]
interval: 10s
timeout: 5s
retries: 3
start_period: 15s
dash:
image: ghcr.io/mofcloud/dash:v2.0.17
restart: unless-stopped
logging: *logging
depends_on:
mof:
condition: service_healthy
ports:
- "80:80"
volumes:
offer-cache:
ghcr.io/mofcloud/mof:v2.0.15ghcr.io/mofcloud/dash:v2.0.17ghcr.io/mofcloud/mof-mcp:v2.0.3Keep the service names mof, mof-mcp and dash. The services find each other by these names (mof:8080, mof-mcp:8001), so nothing else needs configuring; renamed services can’t connect.
Database connection
Fill in your existing PostgreSQL connection in compose.yaml:
RK_POSTGRES_0_ADDR- Address:port
RK_POSTGRES_0_USER- Username
RK_POSTGRES_0_PASS- Password
Existing data and database access
The role needs login and CREATEDB permissions. Changing the address does not migrate data or reset passwords. Back up and restore separately before switching databases.
Start
docker compose config --quiet
docker compose up -d
docker compose psOnce healthy, get the Admin password:
docker compose logs mof | grep "Admin password"Open MOF
http://SERVER_IP/adminInstall your license and create users.
http://SERVER_IPUsers sign in with their MOF accounts.
Connect an AI client through MCP
Enable access in Admin → Settings → MCP. Personal tokens need no OAuth. Browser-based authorization requires public HTTPS and OAuth configuration.