Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Connect Runs on your machine
claude mcp add local-llm-worker -e LLW_BASE_URL=<LLW_BASE_URL> -e LLW_MODEL=<LLW_MODEL> -e LLW_SEARCH_URL=<LLW_SEARCH_URL> -- npx -y [email protected]
{
"mcpServers": {
"local-llm-worker": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LLW_BASE_URL": "<LLW_BASE_URL>",
"LLW_MODEL": "<LLW_MODEL>",
"LLW_SEARCH_URL": "<LLW_SEARCH_URL>"
}
}
}
}
{
"mcpServers": {
"local-llm-worker": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LLW_BASE_URL": "<LLW_BASE_URL>",
"LLW_MODEL": "<LLW_MODEL>",
"LLW_SEARCH_URL": "<LLW_SEARCH_URL>"
}
}
}
}
{
"servers": {
"local-llm-worker": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LLW_BASE_URL": "<LLW_BASE_URL>",
"LLW_MODEL": "<LLW_MODEL>",
"LLW_SEARCH_URL": "<LLW_SEARCH_URL>"
}
}
}
}
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 |
|---|---|
LLW_BASE_URLOptional | Model server URL (Ollama, llama.cpp, LM Studio, vLLM). Default http://localhost:11434 |
LLW_MODELOptional | Model to use; optional if the server has only one |
LLW_SEARCH_URLOptional | SearXNG URL for web research (optional) |
Details
| Package | [email protected] (NPM, stdio) |
| First published | 8 Oct 2026 |
| Last updated | 8 Oct 2026 |
| Registry name | io.github.JoblessJoe/local-llm-worker |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
