PluginBench
MCP Server
Active
MIT

Cortex MCP Server

io.github.abbacusgroup/cortex

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

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

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
JSON config
{
  "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

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

View repository →
MIMIMIR logo

MIMIR

Active

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

2
Python
Apache-2.0
View repository →
PRPromptheus logo

Promptheus

Maintained

AI-powered prompt refinement with adaptive questioning and multi-provider LLM support

17
Python
MIT
View repository →

Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.

0
Python
MIT
View repository →

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

0
TypeScript
View repository →

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