Windsurf LLMIntel Model Lifecycle suggest_replacement
How to: Windsurf LLMIntel Model Lifecycle suggest_replacement
Add LLMIntel Model Lifecycle to Windsurf
-
01
Open ~/.codeium/windsurf/mcp_config.json and merge this in. Keep any servers already there.
{
"mcpServers": {
"model-lifecycle": {
"serverUrl": "https://llmintel.ai/v1/mcp"
}
}
}-
02
Save the file and restart Windsurf.
-
03
Ask for something suggest_replacement does. Windsurf lists the server's tools on connect and calls suggest_replacement itself — you do not invoke it by name.
-
04
If nothing happens, check the server is running and that LLMIntel Model Lifecycle's identifier in your config matches the one above exactly.
Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs
Set these first
LLMIntel Model Lifecycle will not start until these are set, so suggest_replacement never becomes available.
-
LLMINTEL_API_KEY -
LLMINTEL_BASE_URL
Same tool, other clients
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.