Aito runs on your own machine — the client starts it, so there is no endpoint to ping. 694 installs a week from pypi. Last commit 10 Oct 2026.
Predictions over your own data with $p and $why, no model training; says when Aito does not fit.
We read the source, 5 d ago · rules ccca72095570
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
res = subprocess.run(['docker', *args], text=True,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Aito 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 aito -- uvx aito-mcp
{
"mcpServers": {
"aito": {
"args": [
"aito-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.aito]
command = "uvx"
args = ["aito-mcp"]
{
"mcpServers": {
"aito": {
"args": [
"aito-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"aito": {
"args": [
"aito-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
AITO_URL (The Aito instance URL. Optional: without it the server uses the `aito start` profile.), AITO_API_KEY (The instance's API key (a read-only key is enough unless writes are enabled).), AITO_MCP_ALLOW_WRITES (Set to 1 to enable put_schema and upload_rows. Off by default.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models.
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Manage your endurance training data and race preparation
Decision tracking with prediction validation and outcome gates for AI agents
MCP server for AiDataTaskRunner Panel (MT5) - Control data generation and ML model training via MCP
Read-only access to your own Pithflow meeting notes, transcripts, dictionary and usage.
Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Answers built from our own checks of this server.