Advanced / self-hosted
Run your own MCP server
Two servers. One graph. Local for offline, single-file use. Cloud for Postgres-backed, multi-product collaboration. Both open source. Both free.
A single .upg file on your machine.
- Storage
- .upg file (JSON), portable and git-friendly
- Best for
- Solo, offline, version-controlled work
Postgres-backed, built for teams.
- Setup
- Docker · self-hosted, open source
- Storage
- Postgres (multi-product, full-text search)
- Best for
- Teams, collaboration, webhooks
Manual config
Add to your AI tool directly
If you prefer to edit .mcp.json by hand instead of running upg mcp setup, paste this into your project config.
.mcp.json
{
"mcpServers": {
"unified-product-graph": {
"command": "npx",
"args": ["-y", "@unified-product-graph/mcp-server", "--file", "./my-product.upg"]
}
}
}./my-product.upg is your graph file. Omit --file and the server finds a .upg in your workspace, or creates product.upg. Launched over stdio by your AI tool. See the CLI to run it by hand.
Local vs Cloud
Same protocol, different storage
Both servers share most tool signatures. Start local; move to cloud when you need teams.
The mental model
UPG works like Git
Both servers cost nothing to run. The local server reads a file on your disk; the cloud server runs on your own Postgres. Open spec, no lock-in either way.
Local version control
Runs on · Your machine
Local graph queries
Runs on · Your machine
Multi-product graph DB
Runs on · Your infra (Docker)