OpsinTech Platform
OpsinTech Platform — An enterprise-grade AI agent platform built on LangGraph, featuring multi-tenant architecture, role-based access control, sandboxed tool execution, and an admin UI for managing models, MCP servers, skills, and tools. Designed for
What is OpsinTech Platform?
OpsinTech Platform is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to opsintech platform — an enterprise-grade ai agent platform built on langgraph, featuring multi-tenant architecture, role-based access control, sandboxed tool execution, and an admin ui for managing mo...
OpsinTech Platform — An enterprise-grade AI agent platform built on LangGraph, featuring multi-tenant architecture, role-based access control, sandboxed tool execution, and an admin UI for managing models, MCP servers, skills, and tools. Designed for
This server falls under the Business Applications and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- OpsinTech Platform — An enterprise-grade AI agent platform b
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx opsintech-platformConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OpsinTech Platform
OpsinTech Platform is an enterprise-grade AI agent platform built on LangGraph that provides a full multi-tenant environment for deploying, managing, and auditing AI agents at scale. It supports role-based access control with three distinct roles (platform admin, tenant admin, tenant member), sandboxed tool execution in Local, Docker, or Kubernetes modes, built-in MCP server management, skill and tool libraries, and an admin UI. Organizations use it as the infrastructure layer for running production AI agents with full audit trails, model provider flexibility, and tenant isolation.
Prerequisites
- Docker and Docker Compose installed (production deployment path)
- Git for cloning the repository
- make available on your system (build automation)
- An account on at least one supported LLM provider (OpenAI, Anthropic, DeepSeek, Gemini, etc.) for configuring models via the admin UI
Clone the repository
Clone the OpsinTech Platform repository to your local machine or server.
git clone https://github.com/OpsinTech/opsintech-platform.git
cd opsintech-platformGenerate the platform configuration
Run 'make config' to generate the config.yaml file with your database, sandbox mode, and tool group settings.
make configStart the platform
Launch all platform services via Docker Compose. The platform becomes available at http://localhost:2026.
make upComplete initial setup via the admin UI
Open http://localhost:2026 in your browser. The first-run setup wizard will prompt you to set admin credentials. Do not configure models in config.yaml — use the admin UI instead.
Add LLM providers and MCP servers
In the admin UI, navigate to Models to add your LLM provider API keys, and to MCP Servers to register any MCP servers your agents should have access to.
Create tenants and deploy agents
Create tenant organisations, assign users with appropriate roles (platform_admin, tenant_admin, tenant_member), and deploy agents with the skills and tools appropriate for each tenant's use case.
OpsinTech Platform Examples
Client configuration
OpsinTech Platform exposes its own MCP server interface. Connect an external MCP client to the platform's MCP endpoint after deployment.
{
"mcpServers": {
"opsintech": {
"type": "http",
"url": "http://localhost:2026/mcp"
}
}
}Prompts to try
Administrative and operational prompts for interacting with the OpsinTech Platform.
- "List all active tenants and their assigned models."
- "Create a new tenant called 'DataTeam' with the tenant_admin role for user [email protected]."
- "Show the audit log for all tool executions in the last 24 hours."
- "Register the GitHub MCP server for the Engineering tenant."
- "Which agents are currently running and what tasks are they executing?"Troubleshooting OpsinTech Platform
Docker image pull fails during 'make up' due to network issues (common in China).
Pre-pull the base images before building: docker pull python:3.12-slim && docker pull node:22-alpine && docker pull nginx:alpine — then re-run 'make up'.
Cannot log in after the first-run setup wizard.
Ensure you completed the setup wizard fully and set an admin password. If the session expired, restart the containers with 'make up' and access the setup wizard again at http://localhost:2026.
Sandboxed tool execution fails or times out.
Check that your chosen sandbox mode (Local, Docker, or Docker+Kubernetes) is available. For Docker sandbox mode, run 'make docker-init' to pull the required sandbox image before starting the platform.
Frequently Asked Questions about OpsinTech Platform
What is OpsinTech Platform?
OpsinTech Platform is a Model Context Protocol (MCP) server that opsintech platform — an enterprise-grade ai agent platform built on langgraph, featuring multi-tenant architecture, role-based access control, sandboxed tool execution, and an admin ui for managing models, mcp servers, skills, and tools. designed for It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OpsinTech Platform?
Follow the installation instructions on the OpsinTech Platform GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with OpsinTech Platform?
OpsinTech Platform works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OpsinTech Platform free to use?
Yes, OpsinTech Platform is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
OpsinTech Platform Alternatives — Similar Business Applications Servers
Looking for alternatives to OpsinTech Platform? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OpsinTech Platform in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use OpsinTech Platform?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.