Omni Nli

Name: Omni Nli
Author: CogitatorTech

by CogitatorTechcommunityv0.1.1

Omni-NLI is a self-hostable server that provides natural language inference (NLI) capabilities via RESTful and Model Context Protocol (MCP) interfaces.

From the registry: An MCP server for natural language inference

GitHub Repository

Install & configure

Prerequisites

required
Install omni-nli
Install via pip with a backend extra (e.g., huggingface).
```
$ pip install omni-nli[huggingface]
```
required
Start the server
Run the omni-nli CLI to launch the server on port 8000.
```
$ omni-nli
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `omni-nli` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install omni-nli** — Install via pip with a backend extra (e.g., huggingface). Run: `pip install omni-nli[huggingface]`
- **Start the server** — Run the omni-nli CLI to launch the server on port 8000. Run: `omni-nli`

Canonical MCP server config (HTTP transport):
- url: `http://127.0.0.1:8000/mcp/`

Note: Exposes both REST and MCP. Supports Ollama, HuggingFace, and OpenRouter backends.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Exposes both REST and MCP. Supports Ollama, HuggingFace, and OpenRouter backends.