Running local LLMs means choosing between a strong reasoning model and a fast coding model. You can't load both on a single machine. Manually
Running local LLMs means choosing between a strong reasoning model and a fast coding model. You can't load both on a single machine. Manually swapping models kills
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| list_models | Lists all configured models with load status and current mode |
| get_current_model | Returns the alias of the currently loaded model |
| swap_model | Unloads current model, loads the specified one, waits for health check |
| create_model_config | Generates a new launchd plist (macOS) or systemd unit (Linux) for a model |
{
"mcpServers": {
"llama-swap": {
"command": "uvx",
"args": [
"mcp-llama-swap"
],
"env": {
"LLAMA_SWAP_CONFIG": "/path/to/config.json"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| LLAMA_SWAP_CONFIG | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
MCP server for Qubic — balances, prices, transfers, wallets, and more.
Every Pax8 Partner API endpoint, plus an offline store that reconciles billing, tracks MRR, and
Every Domotz endpoint, plus a local SQLite fleet mirror that answers cross-site questions.
Warhammer 40K and Kill Team rules, stats, and game flow MCP server