Catch the LLM/AI calls you didn't need. A fast, deterministic linter that flags LLM API calls where plain code is simpler, cheaper, and more reliable. Your GPT call is a regex.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add overllm -- uvx overllm~/.codex/config.toml
[mcp_servers.overllm]
command = "uvx"
args = ["overllm"]
# codex mcp add overllm -- uvx overllm~/.cursor/mcp.json
{
"mcpServers": {
"overllm": {
"command": "uvx",
"args": [
"overllm"
]
}
}
}.vscode/mcp.json
{
"servers": {
"overllm": {
"type": "stdio",
"command": "uvx",
"args": [
"overllm"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"overllm": {
"command": "uvx",
"args": [
"overllm"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"overllm": {
"command": "uvx",
"args": [
"overllm"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"overllm": {
"command": "uvx",
"args": [
"overllm"
]
}
}
}