VS Code Terradev training_launch_distributed
How to: VS Code Terradev training_launch_distributed
Add Terradev to VS Code
-
01
Open .vscode/mcp.json and merge this in. Keep any servers already there.
{
"servers": {
"terradev": {
"type": "sse",
"url": "https://terradev-mcp.terradev.cloud/sse"
}
}
}-
02
Save the file and restart VS Code.
-
03
Ask for something training_launch_distributed does. VS Code lists the server's tools on connect and calls training_launch_distributed itself — you do not invoke it by name.
-
04
If nothing happens, check the server is running and that Terradev's identifier in your config matches the one above exactly.
Requires agent mode. MCP: Open User Configuration puts the same block in every workspace. VS Code docs
Set these first
Terradev will not start until these are set, so training_launch_distributed never becomes available.
-
RUNPOD_API_KEY -
VAST_API_KEY -
LAMBDA_API_KEY -
HF_TOKEN -
AWS_ACCESS_KEY_ID -
AWS_SECRET_ACCESS_KEY -
GOOGLE_APPLICATION_CREDENTIALS -
TERRADEV_MCP_BEARER_TOKEN
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.