Superagent MCP
SuperAgent is an MCP server that uniformly calls the Codex, Gemini, and Continue CLI agents. It supports parallel task execution, manages preset system prompts, and provides structured tool calls to clients through the MCP protocol.
rating : 2.5 points
downloads : 7.0K
What is SuperAgent MCP?
SuperAgent MCP is an intelligent assistant management tool, acting like an 'AI assistant scheduling center'. Through it, you can connect and use multiple different AI assistants (such as Codex, Gemini, Continue) simultaneously, process multiple tasks in parallel, and view all results in a unified manner. Imagine you have a project that requires code testing, document writing, and code review simultaneously. Traditionally, you would need to open three different AI tools separately, but SuperAgent allows you to initiate these three tasks in one place, and the system will automatically assign them to the most suitable AI assistants for processing.How to use SuperAgent MCP?
Using SuperAgent is very simple: 1. Install SuperAgent in your development environment. 2. Connect through a client that supports the MCP protocol (such as Claude Desktop, Cursor, etc.). 3. Select the AI assistant and preset role to use. 4. Send task instructions, and the system will automatically process them in parallel. 5. View all results in a unified interface. You don't need to learn the individual usage methods of each AI assistant. SuperAgent provides a unified interaction interface.Applicable scenarios
SuperAgent is particularly suitable for the following scenarios: • Development work that requires using multiple AI assistants to handle different tasks simultaneously. • Teams that want to manage the use and role configurations of AI assistants in a unified manner. • Situations where multiple related tasks need to be processed in parallel to improve efficiency. • Reusing optimized AI role configurations (such as technical document writers, code reviewers, etc.). • Switching quickly between the specialties of different AI assistants during the development process.Main features
Unified AI assistant runner
Integrates three AI assistants, Codex, Gemini, and Continue, into one interface. There's no need to install and configure each tool separately. You can select the most suitable assistant based on the task characteristics, or let the system automatically assign one.
Parallel task execution
Supports running multiple AI tasks simultaneously. Each task can have an independent timeout and working directory. The system will automatically manage the task queue, fully utilize computing resources, and significantly improve work efficiency.
AI role library management
Built - in with multiple preset AI role configurations (such as technical document writers, code review experts, etc.). These role configurations are stored locally, and you can view, edit, or create your own exclusive roles.
Tool automatic discovery
The system will automatically detect available AI assistants and role configurations. You can view all available options through simple commands without manually memorizing complex configuration information.
Advantages
One - stop management of multiple AI assistants, reducing the trouble of tool switching
Parallel processing capabilities significantly improve work efficiency
Preset role configurations enable AI assistants to handle specific tasks more professionally
Unified output format facilitates result organization and analysis
Local storage of role configurations protects privacy and supports customization
Limitations
Requires a Node.js 18 or higher environment
The Continue assistant requires an additional configuration file
Initial configuration may require some technical knowledge
The number of parallel tasks is limited by local computing resources
Requires a client that supports the MCP protocol to use
How to use
Install SuperAgent
Install SuperAgent in your development environment through the npm package manager. The installation process will automatically create the necessary configuration directories and preset role files.
Configure the MCP client
Add the SuperAgent server configuration to the MCP client you are using (such as Claude Desktop). Usually, you need to specify the path of SuperAgent in the client's configuration file.
View available tools
After successful connection, first use the list - agents tool to view all available AI assistants and preset roles to understand the system capabilities.
Execute AI tasks
Select the appropriate tool (codex, gemini, or continue) according to the task requirements, set the task parameters, and initiate the execution. You can initiate multiple related tasks simultaneously.
Manage role configurations
You can view, edit, or create new AI role configuration files in the ~/.superagent/agents directory. These files use the Markdown format and contain role descriptions and system prompts.
Usage examples
Parallel code review and document update
After completing the development of a new feature, you need to perform code quality checks and update relevant documents simultaneously. Traditionally, this needs to be done step - by - step, but using SuperAgent can handle them in parallel.
Multi - environment configuration check
The project needs to check the configuration consistency in development, testing, and production environments. Using SuperAgent, you can initiate the same check tasks to multiple AI assistants simultaneously and compare the analysis results of different AIs.
Collaborative generation of technical documents
You need to generate comprehensive technical documents for a complex system, including architecture descriptions, API documentation, and deployment guides. Different chapters can be assigned to different AI roles for processing.
Frequently Asked Questions
Which AI assistants does SuperAgent support?
What is an AI role (agent)? How can I create my own role?
Why does the Continue assistant require additional configuration?
How to control resource usage when executing tasks in parallel?
What is the difference between SuperAgent and directly using AI assistants?
What should I do if I don't see the preset roles after installation?
Related resources
Official documentation of the MCP protocol
Understand the basic concepts and working principles of the Model Context Protocol
SuperAgent GitHub repository
View the source code, submit issues, and participate in development
Official Node.js website
Download and install the Node.js runtime environment (version 18+ is required)
Claude Desktop client
A desktop client that supports the MCP protocol and can be used to connect to SuperAgent
Continue configuration guide
Learn how to configure the Continue CLI to work with SuperAgent

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.5K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.6K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
17.5K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
53.9K
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
51.3K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
24.3K
5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
17.2K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
75.7K
4.7 points
