Cubiczan MCP Server
OfficialClick 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., "@Cubiczan MCP Servercubiczan_analyze market trends for renewable energy"
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.
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.
Related MCP server: AgentPay
Quick Start
pip install -r requirements.txt
export CUBICZAN_API_KEY="your-key"
python server.pyThe 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 |
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 endpointEnter your Cubiczan API key
The model
cubiczan-agentwill appear in your model listEnable tool calling in chat settings
This server cannot be deployed
Maintenance
Related MCP Connectors
Create, watch, pay for and connect hosted AI agent pods on AgentsPodium. Needs an API key.
Connect AI agents to Replynodes over the Model Context Protocol.
Give your AI hands. Identity, credential vault, and API gateway for autonomous agents.
Phone, SMS & email for AI agents — one remote MCP endpoint, OAuth login, zero install.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables offline AI agent automation with embedded local LLM (Qwen 2.5), sandboxed file operations through AgentFS, and dynamic skill loading. Exposes capabilities via MCP with tri-state safety guards for private, air-gapped environments without network connectivity or API costs.-
- AlicenseNot gradedqualityCmaintenanceMCP server for AgentPay — the payment gateway for autonomous AI agents. Fund a wallet once, give your agent the key, and it discovers, provisions, and pays for tool APIs on its own. One key, every tool.112 npm1MIT
- AlicenseBqualityDmaintenanceConnects any MCP-compatible AI client to Letta.ai's stateful agents for agent conversations, memory management, and tool orchestration.1812MIT
- AlicenseNot gradedqualityDmaintenanceEnables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms.8 npmMIT