- Home
- MCP servers
- Foundation Models
Foundation Models
- other
5
GitHub Stars
other
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"phimage-mcp-foundation-models": {
"command": "/path/to/mcp-foundation-models/.build/release/mcp-foundation-models",
"args": [],
"env": {
"DEBUG": "1",
"SYSTEM_INSTRUCTIONS": "Set default system instructions for the AI assistant"
}
}
}
}You can run a local MCP server that exposes Apple Foundation Models for private, on-device text generation. This server lets MCP clients generate text securely without sending data to external services, keeping your prompts and models on your device.
How to use
You connect to the Foundation Models MCP server from your MCP client to perform on-device text generation. Run the local server and point your client to the provided command path. You can optionally customize behavior by setting environment variables to control system instructions and debug logging.
How to install
Prerequisites you need on macOS before building and running the server:
-
macOS 26.0 or later (macOS Tahoe)
-
Xcode 26.0 or later
-
Swift 6.2 or later
-
Apple Silicon Mac (recommended for Foundation Models)
Step-by-step build and run flow:
git clone <repository-url>
cd mcp-foundation-models
swift build -c release
# The executable will be available at:
.build/release/mcp-foundation-models
# Run the server (example command path to use with MCP clients):
./.build/release/mcp-foundation-models
Additional configuration and usage notes
Environment variables you can use to customize the server behavior:
SYSTEM_INSTRUCTIONS=Set default system instructions for the AI assistant
DEBUG=1 # Enable debug logging (any non-empty value)