Safe to run? Will it work? Complete? An A-F grade for any repo, plus a verify loop. Never runs it.
Connect Runs on your machine
claude mcp add code-guardian -e CODE_GUARDIAN_LLM_URL=<CODE_GUARDIAN_LLM_URL> -e CODE_GUARDIAN_LLM_MODEL=<CODE_GUARDIAN_LLM_MODEL> -- uvx code-guardian-mcp==0.7.1
{
"mcpServers": {
"code-guardian": {
"command": "uvx",
"args": [
"code-guardian-mcp==0.7.1"
],
"env": {
"CODE_GUARDIAN_LLM_URL": "<CODE_GUARDIAN_LLM_URL>",
"CODE_GUARDIAN_LLM_MODEL": "<CODE_GUARDIAN_LLM_MODEL>"
}
}
}
}
{
"mcpServers": {
"code-guardian": {
"command": "uvx",
"args": [
"code-guardian-mcp==0.7.1"
],
"env": {
"CODE_GUARDIAN_LLM_URL": "<CODE_GUARDIAN_LLM_URL>",
"CODE_GUARDIAN_LLM_MODEL": "<CODE_GUARDIAN_LLM_MODEL>"
}
}
}
}
{
"servers": {
"code-guardian": {
"type": "stdio",
"command": "uvx",
"args": [
"code-guardian-mcp==0.7.1"
],
"env": {
"CODE_GUARDIAN_LLM_URL": "<CODE_GUARDIAN_LLM_URL>",
"CODE_GUARDIAN_LLM_MODEL": "<CODE_GUARDIAN_LLM_MODEL>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
CODE_GUARDIAN_LLM_URLOptional | Optional: local model for the explain tool (Ollama /api/chat or an OpenAI-compatible /v1/chat/completions URL) |
CODE_GUARDIAN_LLM_MODELOptional | Optional: model name for the explain tool |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 12 Nov 2026 |
| Last updated | 12 Nov 2026 |
| Registry name | io.github.LuminariSoftwares/code-guardian |
More developer tools servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
