omlx-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
omlx-mcp
English | 日本語
A minimal stdio MCP server that lets Claude (or any MCP client) run prompts on a local oMLX instance through its OpenAI-compatible API.
Tools
Tool | Purpose |
| Loaded models, default model, power state, and recent jobs |
| Run a prompt. Waits up to |
| Fetch a job's result, waiting up to 50 seconds if it is still running |
| Cancel a running job |
Design notes:
Waits are capped at 50 seconds so calls stay inside the 60-second timeout that some MCP bridges enforce. Longer generations keep running as jobs and can be polled with
omlx_result.thinking=false(the default) sendschat_template_kwargs.enable_thinking=false. Ifenable_thinkingis pinned in oMLX's per-model settings, that setting wins.Responses contain only the answer text,
finish_reason, and a usage summary. Reasoning is included only withinclude_reasoning=true.contextis placed before the prompt, so repeated calls over the same material reuse oMLX's prefix cache.On battery power, runs are refused unless
allow_on_battery=true.Jobs are stored as
~/.omlx-mcp/jobs/*.json. Jobs that were running when the server restarted are markedlost. The latest 100 jobs are kept.No tool calling (web search etc.). Plain generation only.
Related MCP server: CascadeGateway
Environment variables
Variable | Default |
|
|
| none |
| first entry of |
|
|
Setup
git clone https://github.com/chsh/omlx-mcp.git
cd omlx-mcp
uv sync --dev
uv run pytest -qRegistering with Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"omlx": {
"command": "/opt/homebrew/bin/uv",
"args": ["run", "--directory", "/absolute/path/to/omlx-mcp", "omlx-mcp"],
"env": {
"OMLX_BASE_URL": "http://127.0.0.1:8000/v1",
"OMLX_API_KEY": ""
}
}
}
}Use absolute paths for both uv and the repository (check with which uv and pwd). Processes launched by Claude Desktop get a minimal PATH.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables integration of local LLM capabilities with MCP-compatible clients like Claude Desktop, Continue.dev, and Cline. Provides tools for processing text prompts through local language models using a customizable inference function.21-
- AlicenseAqualityBmaintenanceProvides an MCP endpoint that lets clients like Google Antigravity and Claude Desktop dispatch LLM tasks to local GPU models with automatic hardware-adaptive routing and cloud fallback, enabling near-zero token cost execution.34MIT
- AlicenseBqualityCmaintenanceEnables orchestration of OpenAI-compatible GLM and other model endpoints via MCP, supporting streaming, background runs, cancellation, and local run history, with an optional bridge to other MCP servers.20ISC
- AlicenseAqualityFmaintenanceLets MCP clients delegate private or bulk text tasks to a local OpenAI-compatible LLM while keeping data on the machine.11MIT