Localmodels runs on your own machine — the client starts it, so there is no endpoint to ping. 334 installs a week from npm. Last commit 2 Nov 2026.
Talk to a local Ollama server: list, pull, inspect, generate, chat and embed.
Today is the operative word: we check Localmodels 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 localmodels -- npx -y @reneturcios/localmodels
{
"mcpServers": {
"localmodels": {
"command": "npx",
"args": [
"-y",
"@reneturcios/localmodels"
]
}
}
}
[mcp_servers.localmodels]
command = "npx"
args = ["-y", "@reneturcios/localmodels"]
{
"mcpServers": {
"localmodels": {
"command": "npx",
"args": [
"-y",
"@reneturcios/localmodels"
]
}
}
}
{
"servers": {
"localmodels": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/localmodels"
]
}
}
}
Inspect, validate and preview VRM / VRMA files from an AI agent (5 tools, local stdio server).
Generate and edit images with Labnana through a local MCP server with MCP Apps previews.
Tiny local MCP notes server in Python: create, list, and search notes stored in a local JSON file.
Verify docs against code, detect drift, and generate verified specs (MCP server).
List Documentero templates, inspect field schemas, and generate Word/PDF/Excel documents.
MCP Server that generate video call url
A Codex stdio MCP server that generates repo-local tldraw diagrams and detects code graph drift.
Local MCP gateway daemon: route, audit, and inspect MCP servers from one config.
Answers built from our own checks of this server.