Neo0 MCP Server
A coordinate-based semantic addressing system for AI agents, providing tools to derive immutable addresses, search concepts, and manage personae via the Model Context Protocol.
README
Neo0 MCP
๐ Try the live demo ยท ๐ Read the whitepaper
<img width="1342" height="1141" alt="neo0mcp" src="https://github.com/user-attachments/assets/11e7ee2e-d4ca-4f4b-abbf-bbd0c0044530" />
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 โ 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 โ coordinate derivation, the immutable registry, persona control โ runs as a hosted service and is not included here.
Architecture
MCP client (Claude) โโถ neo0-mcp (this repo, :8000) โโHTTPโโโถ 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.
Tools
| Tool | Description |
|---|---|
neo0_info |
Engine overview and load status |
derive_address |
Immutable coordinate address + prefix region for a concept |
search |
k nearest concepts, each with its address |
semantic_region |
Members of a prefix region |
verify_address |
Tamper check by re-deriving from the minting-time basis |
prefix_proximity |
Prefix-match length + cosine similarity between two concepts |
persona |
Region characteristic concepts + coherence-based control parameters |
compose_persona |
Model ร persona composition โ coming soon |
Quick start
pip install -r requirements.txt
cp .env.example .env # then set NEO0_API_URL and NEO0_API_KEY
python server.py
The server speaks streamable-HTTP MCP on port 8000 at path /mcp.
Use with Claude
In Claude: Settings โ Connectors โ Add custom connector, then enter your server URL ending in /mcp.
Configuration
| Variable | Description |
|---|---|
NEO0_API_URL |
Neo0 engine API base URL |
NEO0_API_KEY |
Engine API key |
License
This MCP shell is licensed under Apache-2.0 (see LICENSE).
The Neo0 coordinate engine is patent-pending and provided as a hosted API under separate terms. Use of the API includes a license to the relevant patents; independently reimplementing the engine is not covered by this repository's license.
Built by Neo0 โ https://neo0.ai
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.