HarnessXGate MCP Server
Integrates GitHub Copilot CLI as one of the AI engines, allowing HarnessXGate to route prompts to Copilot, check engine readiness, and automatically fail over to other engines when unavailable.
Integrates Ollama as a local/offline AI engine, enabling prompts to be routed to locally pulled models, with health/status checks and automatic failover.
Supports OpenAI-compatible API endpoints as AI engines, configured via URL and API key, enabling prompt routing and automatic failover across compatible providers.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
HarnessXGate
Free AI multi-engine router, live web dashboard, and MCP server — zero dependencies, one command to install.
Built so anyone (even without an expensive AI subscription) can combine free AI engines (OpenCode, GitHub Copilot CLI, FreeLLMAPI / OpenAI-compatible APIs, and Ollama) behind one simple web page, one CLI (hxg), and one MCP tool. When one model hits a rate limit or goes offline, HarnessXGate automatically switches to the next best free model without stopping your work.
One-Command Install (Opens the Web App Automatically)
Windows — Command Prompt (cmd)
curl -fsSL https://raw.githubusercontent.com/Eli-Mira/HarnessXGate/main/install.cmd -o "%TEMP%\hxg.cmd" && "%TEMP%\hxg.cmd"Windows — PowerShell
irm https://raw.githubusercontent.com/Eli-Mira/HarnessXGate/main/install.ps1 | iexmacOS / Linux / WSL
curl -fsSL https://raw.githubusercontent.com/Eli-Mira/HarnessXGate/main/install.sh | bashOr via pip
pip install git+https://github.com/Eli-Mira/HarnessXGate.git
hxgRequirements: Only Python 3.10+ (zero extra
pippackages needed!).
Related MCP server: forge-mcp
How to Use (For Beginners — 30 Seconds)
Open the Dashboard: Type
hxgin your terminal (openshttp://127.0.0.1:7878in your browser).Check Your Engines: You only need one green (
Ready) engine to start:OpenCode (Free):
curl -fsSL https://opencode.ai/install | bashOllama (100% Offline & Free): Install from ollama.com and run
ollama pull qwen2.5-coderGitHub Copilot CLI:
copilot loginFreeLLMAPI / OpenRouter / Groq: Run
hxg setupand paste your URL + API key.
Ask Anything: Type your question in the Quick Ask box on the web dashboard (or run
hxg ask "Explain recursion simply"in your terminal).
CLI Commands
Command | What it does |
| Starts the live web dashboard at |
| Runs a prompt with automatic model & engine failover ( |
| Shows which AI engines are ready right now |
| Shows active running workers, engine counts, and recent events |
| Opens a live auto-refreshing terminal monitor |
| 30-second guided setup wizard for API URLs & keys |
| Runs the stdio MCP server ( |
Connect to AI Coding Tools (MCP)
Antigravity (agy)
agy mcp add harnessxgate hxg mcpClaude Desktop / Cursor / Hermes
Add to your MCP config:
{
"mcpServers": {
"harnessxgate": {
"command": "hxg",
"args": ["mcp"]
}
}
}Privacy & Safety
Runs 100% locally on
127.0.0.1— zero cloud telemetry, zero tracking.API keys are read from environment variables or
~/.harnessxgate/.envin memory only and never logged.
License
MIT — built by EliLain.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to perform local code search, indexing, and analysis across Java, JavaScript/TypeScript, .NET/C#, and Python projects through the MCP protocol.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA production-grade, LLM-agnostic local development engine over MCP, providing structured code intelligence and shared language server processes for AI coding agents.MIT
- AlicenseAqualityDmaintenanceA lightweight MCP server that enables AI assistants to execute local development tools and retrieve system status with low latency over stdio or HTTP.13MIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.-