Local LLM Worker MCP server

local-llm-worker

Let Claude hand the bulk reading to your local LLM: test logs, big files, web pages. Claude only gets the answer.

Works with Ollama · llama.cpp · LM Studio · vLLM · LocalAI · any OpenAI-compatible endpoint

Reading a 5,000-line test log or three docs pages costs the same frontier-model tokens as hard architectural work. local-llm-worker is an MCP server and Claude Code plugin that moves that bulk work onto the GPU (or CPU) you already own:

the answer.

• offload: your local model runs the noisy command or reads the big file. Claude gets

cited answer. Claude never sees the pages.

• research: your local model searches the web, reads the pages in full and returns a

and retries until a test Claude wrote first passes. Claude gets a one-line verdict, not the code.

• delegate (opt-in): your local model writes one file in an isolated git worktree

> offload  npm test 2>&1   "Which test fails, and why?"
`fixed coupon never goes below zero` (test/cart.test.js:404): applyCoupon(5, {type:'fixed',
value:10}) returns -5, expected 0.
— qwen3-coder:30b-a3b-q4_K_M · 19,132 input tokens read locally

Why

slower.

• Any model, any hardware. No hardcoded models, no GPU assumptions. CPU-only works, just

The concurrency limit is a config value, not a hardcoded lock.

• Parallel by default. Several calls in one turn, or from several subagents, run at once.

text (number-heavy logs need more tokens than prose). Anything cut is reported.

• Fits the context automatically. Material is sized to the model's context window per

and changes any setting. It takes effect on the next call, with no restart.

• Zero dependencies. Plain Node ≥ 18. Installing from git needs no npm install.
• Agent-configurable. One configure call shows the config, the backend and its models,

Install

Prerequisites: Node ≥ 18, git, and a running local model server (e.g. ollama pull qwen3-coder:30b).

Claude Code plugin

/plugin marketplace add JoblessJoe/local-llm-worker
/plugin install local-llm-worker@local-llm-worker

Then just ask: "set up local-llm-worker for my machine". Claude finds your backend, picks a model, and asks which tools it should use on its own (auto_use). By default that's offload and research; delegate is opt-in. Every tool also works whenever you ask for it.

Make Claude use it every time

A session-start reminder nudges Claude toward the tools you chose. For dependable use, add this to your CLAUDE.md; setup offers to do it for you:

Shortened. The full README is on GitHub.