Operandi runs on your own machine — the client starts it, so there is no endpoint to ping. 137 installs a week from pypi. Last commit 22 Jul 2026.
Grounded, safety-checked appliance operation packages for robots and agents. Zero-config trial.
Today is the operative word: we check Operandi 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 operandi -- uvx operandi-mcp
{
"mcpServers": {
"operandi": {
"command": "uvx",
"args": [
"operandi-mcp"
]
}
}
}
[mcp_servers.operandi]
command = "uvx"
args = ["operandi-mcp"]
{
"mcpServers": {
"operandi": {
"command": "uvx",
"args": [
"operandi-mcp"
]
}
}
}
{
"servers": {
"operandi": {
"type": "stdio",
"command": "uvx",
"args": [
"operandi-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
OPERANDI_API_URL (Base URL of the OPERANDI API (default https://api.operandi.cc; use your hosted URL in prod)), OPERANDI_API_KEY (Optional: your OPERANDI key. Leave unset for a zero-config instant trial (the server mints + caches its own key, 2 packages included)).
Zendesk configuration management for AI agents: propose, review, apply and roll back changes.
Trust verification for agents and packages: safety scans, signed scores, identity and badges.
Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site.
Music distribution for agents: upload, AI-check, submit and track releases on ONCE.
Sanctions screening and PEP checks via OpenSanctions API for AI agents
Generate, validate and check robots.txt rules for AI crawlers. Free; optional Pro key.
ERC-7303 token-controlled roles for AI agents: grant, check, and revoke permissions on-chain
Safety checks for trading bots: Solana and Robinhood Chain rug-checks, launch feed, safe_buy.
Answers built from our own checks of this server.