Offline MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 241 installs a week from pypi. Last commit 27 Oct 2026.
Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.
Today is the operative word: we check Offline MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add offline-mcp -- uvx offline-mcp
{
"mcpServers": {
"offline-mcp": {
"command": "uvx",
"args": [
"offline-mcp"
]
}
}
}
[mcp_servers.offline-mcp]
command = "uvx"
args = ["offline-mcp"]
{
"mcpServers": {
"offline-mcp": {
"command": "uvx",
"args": [
"offline-mcp"
]
}
}
}
{
"servers": {
"offline-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"offline-mcp"
]
}
}
}
Browser-local and CLI static evidence for deployed AI model artifacts.
Local MCP tools for secret status and guarded deployment. Values never reach the agent.
Reference MCP stdio server for observing Vercel projects and deployments.
MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI
AI agent tools for FreeAppStore: deploy status, SDK docs, app info, platform guide.
Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Manage your Onde Inference account and models: apps, model catalog, fine-tuned GGUF deploys.
Build, deploy, and sell AI agents for local-service businesses - from your IDE.
Answers built from our own checks of this server.