An MCP server for natural language inference
An MCP server for natural language inference
Given two pieces of text called premise and hypothesis, NLI (AKA textual entailment) is the task of determining the directional relationship between them as it is perceived by a human reader. The relationship is given one of these three labels:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"omni-nli": {
"command": "uvx",
"args": ["omni-nli"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Secure, fragment-based long-term memory for MCP-compatible AI agents.
Temporal knowledge graph of your codebase (Graphiti + Neo4j), served to AI agents via MCP.
MCP Server for Obsidian Vault Access via Local REST API
Ghost-MCP is an injectable MCP (Model Context Protocol) server for vibe reverse engineering assistant on Windows. It combines memory inspection