Cubiczan MCP Server
Connects Off Grid mobile app to Cubiczan's multi-agent intelligence, exposing agent orchestration as an OpenAI-compatible API endpoint.
README
Cubiczan MCP Server
Connect your Off Grid mobile app to Cubiczan's multi-agent intelligence.
What it does
Exposes Cubiczan's agent orchestration capabilities (CHP consensus, multi-agent workflows, stigmergic coordination) as an OpenAI-compatible API endpoint that Off Grid phones discover via LAN or connect to manually.
Quick Start
pip install -r requirements.txt
export CUBICZAN_API_KEY="your-key"
python server.py
The server starts on 0.0.0.0:8080 and implements the OpenAI /v1/chat/completions endpoint.
How it works
| Off Grid Client | Cubiczan MCP Server |
|---|---|
| Remote LLM Server (OpenAI-compatible) | FastAPI serving /v1/models + /v1/chat/completions |
| Tool calling enabled | Returns function calls for Cubiczan agents |
| LAN discovery (port 8080) | Responds to HTTP probes on /v1/models |
| Secure keychain API key storage | Validates API key from Authorization header |
Available Tools
The server exposes Cubiczan's agent capabilities as OpenAI function tools:
cubiczan_analyze— Run multi-agent analysis on a problemcubiczan_consensus— Run CHP governance consensus on a proposalcubiczan_swarm— Deploy a stigmergic swarm for continuous monitoringcubiczan_search— Search Cubiczan knowledge baseweb_search— Real web searchread_url— Fetch and summarize a URL
Adding to Off Grid
- Open Off Grid → Settings → Remote Servers → Add Server
- Enter
http://<host>:8080as the endpoint - Enter your Cubiczan API key
- The model
cubiczan-agentwill appear in your model list - Enable tool calling in chat settings
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.