io.github.CogitatorTech/omni-nli

An MCP server for natural language inference

not probed in the official registry, not probed

Run it: uvx omni-nli@0.1.1 (stdio, probed in a container with the network off)
Host: pypi.org
Repository: https://github.com/CogitatorTech/omni-nli
Registry: active, updated 2026-02-23 · registry entry

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Semantic Cache MCP io.github.CoderDayton/semantic-cache-mcp · alive
io.github.Codeturion/codesurface · needs mcp<2
Unity API Documentation io.github.Codeturion/unity-api-mcp · alive
Unreal Engine API Documentation io.github.Codeturion/unreal-api-mcp · alive
Agent Coherence — Stale Write Guard (FS) io.github.Cohexa-ai/stale-write-guard-fs · crashed on start
io.github.ColinHughes2121/gocreative-wedge-mcp · needs mcp<2
YApi MCP io.github.ContextDong/yapi-mcp · alive
io.github.Contextual-Laboratories/contextual · not found

Servers that mention omni.

OmniSignal ai.omnisignal/omnisignal · needs auth
travelMCP Directory ai.omnitravel/travelmcp-directory · alive
OmniaAuto — Canadian Vehicle Listings ca.omniaauto/listings-canada · needs auth
Project Sairen - Agentic Execution Node ca.omniapps/sairen · alive
com.clauxel.geminiomnirights/geminiomnirights-mcp · no DNS
Faber Machine Market com.fabersomniorum/faber-machine-market · not MCP
Omnicall — Agent Tools Gateway com.gocreativeai.omnicall/agent-tools · server error
com.infobip/mcp · needs auth

Badge for the README

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

The entry has only a package that serves streamable-http. The probe starts packages that talk over stdio only. The entry is on the board so that the list holds the whole registry and says what it does not check.