omlx-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@omlx-mcp-server What models are available and what's the power status?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
omlx-mcp-server
Local stdio MCP server for oMLX.
Tools
omlx_status: return the localoMLXmodel list and current power status in one call.omlx_run: unified execution tool for eitherchatoragentmode.
Related MCP server: local-mcp
Battery Guard
omlx_run checks power status before using a model.
On AC power: execute normally.
On battery power: return
status="needs_confirmation"unlessallow_on_battery=true.
This is meant to force an explicit user decision before running heavy local inference on battery.
Compact Interface
The server is intentionally compressed to two tools to keep MCP schema overhead down.
Use
omlx_status()to fetchmodels + power_status.Use
omlx_run(mode="chat" | "agent", prompt=...)for execution.
omlx_run picks a default model automatically:
chatmode defaults toMLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bitagentmode defaults toMLX-Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-8bit
Defaults
Default chat model:
MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bitDefault agent model:
MLX-Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-8bitDefault base URL:
http://127.0.0.1:8000/v1
Local Run
UV_CACHE_DIR=.uv-cache UV_PROJECT_ENVIRONMENT=.venv uv sync --dev
UV_CACHE_DIR=.uv-cache UV_PROJECT_ENVIRONMENT=.venv uv run omlx-mcp-serverCodex Config Snippet
Add this to your Codex config if you want future sessions to discover it automatically. Replace /path/to/omlx-mcp-server with your clone path and set your local oMLX key:
[mcp_servers.omlx]
command = "uv"
args = [
"run",
"--directory", "/path/to/omlx-mcp-server",
"omlx-mcp-server",
]
[mcp_servers.omlx.env]
UV_CACHE_DIR = "/path/to/omlx-mcp-server/.uv-cache"
UV_PROJECT_ENVIRONMENT = "/path/to/omlx-mcp-server/.venv"
OMLX_BASE_URL = "http://127.0.0.1:8000/v1"
OMLX_API_KEY = "your-local-omlx-key"
OMLX_DEFAULT_MODEL = "MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit"
OMLX_AGENT_MODEL = "MLX-Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-8bit"Available Tools
2 toolsomlx_runB
Run either a chat or agent-style local oMLX request. Blocks on battery unless allow_on_battery is true.
Inputs: mode (required), prompt (required), model, context, +4 more. Returns: object
omlx_statusA
Return local oMLX model list and current Mac power status.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one for querying status/model list, the other for running requests. There is no overlap or ambiguity.
Both tools follow a consistent 'omlx_' prefix plus a verb (status, run). This is a clear and predictable pattern.
With only 2 tools, the set feels thin for a model-running server. While each tool is justified, the count is on the borderline of being too minimal.
The core functionality is covered: status provides information needed before running, and run executes the request. Minor gaps exist (e.g., no explicit model management or request cancellation), but for the stated purpose the surface is largely complete.
Maintenance
Related MCP Connectors
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA Python MCP server that exposes local Ollama models as tools for AI assistants, enabling chat, generation, embeddings, and model management without cloud APIs.83 PyPI5MIT
- FlicenseNot gradedqualityDmaintenanceEnables running MCP tools against local MLX models on your Mac, with hardware-aware configuration, CLI streaming, and a dashboard for routing and monitoring.5,198 npm-
- AlicenseNot gradedqualityDmaintenanceMCP server that enables local Apple on-device Foundation Model access via any MCP client, supporting text generation, structured output, and multi-turn chat on macOS.2MIT
- FlicenseAqualityDmaintenanceMCP server that connects LLM agents to a local LM Studio instance, enabling model management, OpenAI-compatible chat completions, text completions, and embeddings through a set of tools.91-