It lets an agent use selected local models without relying only on a hosted model. The required provider settings define where requests go and which models are allowed.

local-model-workers — MCP server by gaabrielrd/local-model-workers-mcp

local-model-workers

local-model-workers is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from gaabrielrd/local-model-workers-mcp. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that sends requests to configured language models running on another local or private computer. The supplied configuration allows specific models through an LM Studio provider.

In plain words

What is it for?: Connecting coding-agent workflows to LM Studio models, choosing permitted local models, and routing requests through a configured provider.
Why use it?: It lets an agent use selected local models without relying only on a hosted model. The required provider settings define where requests go and which models are allowed.

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

Good fit Connecting coding-agent workflows to LM Studio models, choosing permitted local models, and routing requests through a configured provider.

Compare 6 mcp servers from other repositories ↓

Install with agentmods

npx agentmods add mcp/gaabrielrd/local-model-workers-mcp/local-model-workers

Installing this writes the configuration, not the program: `local-model-workers-mcp` has to be on your PATH already, or the server will not start.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/gaabrielrd/local-model-workers-mcp

Installing this writes the configuration, not the program: `local-model-workers-mcp` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers/github.svg)](https://agentmods.dev/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers)

Your own site

<a href="https://agentmods.dev/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers"><img src="https://agentmods.dev/badge/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers"><img src="https://agentmods.dev/badge/mcp/gaabrielrd/local-model-workers-mcp/local-model-workers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

local-model-workers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 9 lines

What it actually says

{
  "local-model-workers": {
    "command": "local-model-workers-mcp",
    "args": [],
    "env": {
      "LMW_PROVIDERS": "[{\"name\":\"lm-studio\",\"type\":\"lm-studio\",\"base_url\":\"http://pc-gabriel.local:1234/v1\",\"allowed_models\":[\"qwen/qwen3.5-9b\",\"google/gemma-4-12b-qat\"],\"priority\":0,\"tls_verify\":false}]"
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 9 lines scan A ff1c099af00d

Subscribe to this mod's changes

local-model-workers is an MCP server published in the GitHub repository gaabrielrd/local-model-workers-mcp (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Data and AI

local-model-workers next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
local-model-workersgaabrielrd/local-model-workers-mcp	MCP server	1	3mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
knowledge_cataloggemini-cli-extensions/data-agent-kit-starter-pack	MCP server	248	yesterday	Apache-2.0	A	—	Claude Code
dataprocgemini-cli-extensions/data-agent-kit-starter-pack	MCP server	248	yesterday	Apache-2.0	A	—	Claude Code
Pineconespacehendrix/clauder	MCP server	59	23d ago	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
rag-ratcq27-dev/rag-rat	MCP server	26	29d ago	MIT	A	—	Claude Code
hubmeshDemigodDSK/hubmesh	MCP server	2	9d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
mcp-server-deapideapi-ai/mcp-server-deapi	MCP server	1	2d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode