core
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
claude mcp add --transport stdio opensumi-core node path/to/server.js \ --env PORT="3000"
How to use
OpenSumi Core is a foundational framework for building AI-native IDE experiences. This MCP server exposes core development and integration capabilities used by the OpenSumi ecosystem to coordinate tooling, extensions, and UI components. You can leverage the server to discover and interact with core services, such as the IDE core runtime, extension system, and common utilities that power OpenSumi-based IDEs. The MCP client integration enables tooling to request capabilities, exchange model context, and orchestrate actions across the IDE environment. Typical usage involves starting the server in your environment and connecting an MCP client to query available tools, channels, and commands exposed by the core framework, then invoking those tools to accelerate development workflows within AI-assisted IDEs.
How to install
Prerequisites:
- Node.js (LTS version) installed on your machine
- Git installed
- Optional: Yarn if you prefer it over npm for package management
Installation steps:
-
Clone the repository: git clone https://github.com/opensumi/core.git cd core
-
Install dependencies: npm install
or if you prefer yarn:
yarn install
-
Build the project (if applicable) or install peer dependencies as recommended in the repository: npm run build
or
yarn build
-
Start the MCP server (example, adjust path to your server entry as needed): npm run start
or, if using the provided configuration, you may run:
node path/to/server.js
-
Verify the server is running and accessible via the configured port and MCP client tooling.
Note: Refer to the repository's CONTRIBUTING.md or documentation for any environment-specific setup (e.g., development environment prerequisites).
Additional notes
Tips and common issues:
- Ensure Node.js version matches the project’s compatibility requirements.
- If the server binds to a specific port, set PORT accordingly (as shown in the mcp_config examples).
- When integrating with MCP clients, confirm the server name matches the configured key (e.g., opensumi-core).
- If you encounter module resolution errors, run a clean install (delete node_modules and reinstall).
- For environment variables, provide placeholders as needed (e.g., API keys or feature flags) and avoid committing secrets to version control.
- Review documentation under CONTRIBUTING.md for development environment preparation and contribution guidelines.
Related MCP Servers
better-chatbot
Just a Better Chatbot. Powered by Agent & MCP & Workflows.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
CanvasMCPClient
Canvas MCP Client is an open-source, self-hostable dashboard application built around an infinite, zoomable, and pannable canvas. It provides a unified interface for interacting with multiple MCP (Model Context Protocol) servers through a flexible, widget-based system.
mcpcat-python-sdk
MCPcat is an analytics platform for MCP server owners 🐱.
zerodha
Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)
unity
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.