Omni Nli runs on your own machine — the client starts it, so there is no endpoint to ping. 97 installs a week from pypi. Last commit 23 Feb 2026.
An MCP server for natural language inference
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 omni-nli -- uvx omni-nli
{
"mcpServers": {
"omni-nli": {
"args": [
"omni-nli"
],
"command": "uvx"
}
}
}
[mcp_servers.omni-nli]
command = "uvx"
args = ["omni-nli"]
{
"mcpServers": {
"omni-nli": {
"args": [
"omni-nli"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"omni-nli": {
"args": [
"omni-nli"
],
"command": "uvx"
}
}
}
Answers built from our own checks of this server.