Local LLM Worker MCP Server
by joblessjoeio.github.JoblessJoe/local-llm-workerv0.1.4
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
context tax
queued
security
queued
cold start
queued
freshness
Active2d ago
Install Local LLM Worker MCP server
Install in Claude Code
claude mcp add local-llm-worker -- npx -y local-llm-workerInstall in Cursor
{
"mcpServers": {
"local-llm-worker": {
"command": "npx",
"args": [
"-y",
"local-llm-worker"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"local-llm-worker": {
"command": "npx",
"args": [
"-y",
"local-llm-worker"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"local-llm-worker": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"local-llm-worker"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"local-llm-worker": {
"command": "npx",
"args": [
"-y",
"local-llm-worker"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Configuration
| Variable | Required | Secret | Description |
|---|---|---|---|
| LLW_BASE_URL | — | — | Model server URL (Ollama, llama.cpp, LM Studio, vLLM). Default http://localhost:11434 |
| LLW_MODEL | — | — | Model to use; optional if the server has only one |
| LLW_SEARCH_URL | — | — | SearXNG URL for web research (optional) |
Freshness
Active — last maintenance signal 2d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-08 · 2d ago · GitHub
Latest release
2026-10-06 · 4d ago · GitHub · v0.1.4
Package published
no data · npm/PyPI
Registry entry updated
2026-10-08 · 2d ago · official registry · v0.1.4
FAQ
›How do I install the Local LLM Worker MCP server in Claude Code?
Run: claude mcp add local-llm-worker -- npx -y local-llm-worker. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Local LLM Worker require an API key?
No required environment variables are declared in its published metadata.
›Can I use Local LLM Worker as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Local LLM Worker in the official MCP registry?
Yes, as io.github.JoblessJoe/local-llm-worker.
Alternatives to Local LLM Worker
Other monitoring & observability MCP servers.