Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Neo0 MCP Server derive address for artificial intelligence"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Coordinate-based semantic addressing for AI agents, exposed over the Model Context Protocol (MCP).
Neo0 assigns every concept an immutable coordinate address in a recursively partitioned semantic space. Concepts that are close in meaning share a coordinate prefix, so the address itself encodes meaning, location, and routing — no separate ontology graph required.
This repository is the open MCP shell. It exposes Neo0's tools to any MCP client (Claude and others) and forwards each call to the Neo0 engine API. The engine itself — coordinate derivation, the immutable registry, persona control — runs as a hosted service and is not included here.
MCP client (Claude) ─▶ neo0-mcp (this repo, :8000) ──HTTP──▶ Neo0 engine API (hosted)The shell holds no engine logic, model weights, or data. It only formats requests and responses; all computation happens behind the engine API. Forking this repository gives you the interface, not the engine.
Related MCP server: LogicMem MCP Server
Tool | Description |
| Engine overview and load status |
| Immutable coordinate address + prefix region for a concept |
| k nearest concepts, each with its address |
| Members of a prefix region |
| Tamper check by re-deriving from the minting-time basis |
| Prefix-match length + cosine similarity between two concepts |
| Region characteristic concepts + coherence-based control parameters |
| Model × persona composition — coming soon |
pip install -r requirements.txt
cp .env.example .env # then set NEO0_API_URL and NEO0_API_KEY
python server.pyThe server speaks streamable-HTTP MCP on port 8000 at path /mcp.
In Claude: Settings → Connectors → Add custom connector, then enter your server URL ending in /mcp.
Variable | Description |
| Neo0 engine API base URL |
| Engine API key |
This MCP shell is provided for evaluation only — see LICENSE. No patent license is granted by this repository; rights are reserved.
The Neo0 coordinate engine is patent-pending and provided as a hosted API under separate terms. Use of the API may include a limited patent license; independently reimplementing the engine is not covered.
© 2026 Seungchul Lee — https://neo0.ai
This server cannot be deployed
Signed agent identity, trust scoring, credit economy, and social layer for AI agents.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
InfoLang semantic memory MCP — investigate, memorize, and recall compressed agent context.
