MCP Server

Active

MIT

Cortex MCP Server

io.github.abbacusgroup/cortex

Local-first persistent knowledge system with OWL-RL reasoning and 22 MCP tools.

What is the Cortex MCP server?

The Cortex MCP server is a persistent knowledge system that provides OWL-RL reasoning capabilities and 22 integrated MCP tools for local-first knowledge management. It enables AI agents to store, query, and reason over structured knowledge without external dependencies.

Cortex is a knowledge management system designed for local deployment. It combines persistent storage with OWL-RL (Web Ontology Language with Rule Language) reasoning to support intelligent knowledge representation and inference. The server exposes 22 tools that allow AI agents to interact with and reason over knowledge graphs.

How to install Cortex

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "cortex": {
      "command": "uvx",
      "args": [
        "abbacus-cortex"
      ]
    }
  }
}

Use cases

Build and maintain knowledge graphs for domain-specific reasoning
Store and retrieve structured facts with semantic inference
Implement rule-based reasoning over persistent knowledge bases
Create local knowledge systems for AI agent augmentation
Query complex relationships in structured data without external APIs

Cortex MCP server FAQ

What is the Cortex MCP server?

Cortex is a local-first persistent knowledge system that provides OWL-RL reasoning and 22 MCP tools for knowledge management and semantic inference.

Is Cortex free to use?

Yes, Cortex is open-source and available on PyPI as 'abbacus-cortex'.

How do I install Cortex?

Install via pip: `pip install abbacus-cortex`, then configure it in your MCP client (Cursor, Claude Desktop, etc.) to connect to the local server.

Does Cortex require authentication?

No, Cortex is designed as a local-first system and does not require external authentication.

What reasoning capabilities does Cortex provide?

Cortex implements OWL-RL (Web Ontology Language with Rule Language) reasoning, enabling semantic inference and rule-based logic over knowledge graphs.

Can I use Cortex offline?

Yes, Cortex is fully local-first and operates entirely offline without external dependencies.

Related MCP servers

io.github.abcxz/conviction-mcp

The arena where AI agents compete for real returns. Prompt a strategy.

View repository →

io.github.abd3lraouf-studios/app-store-connect-mcp

Active

App Store Connect + StoreKit 2: 1,293 Apple operations behind 11 tools, writes confirmed.

TypeScript

View repository →

MIMIR

Active

Typed, calibrated and certified decisions over a context, with abstention and evidence.

Python

Apache-2.0

View repository →

DreamThreads DreamGraph

Parse dreams into structured context and search DreamGraph concepts without storing dream text.

io.github.abe238/hotin

Active

What's hot in AI right now, ranked with receipts from GitHub, HN, npm and Hugging Face.

Python

Apache-2.0

View repository →

CodePic

Active

AI agent draws editable hand-drawn diagrams (flowchart, ER, architecture) via MCP, not static images

MIT

View repository →