agent-mcp
Click 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., "@agent-mcpreview the code in src/main.py for vulnerabilities"
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.
MCP Agent Team
A multi-agent system for collaborative development using the MCP (Model Context Protocol).
Architecture
agent-mcp/
├── mcp-server/ # MCP protocol server
├── agents/ # Specialized AI agents
├── memory/ # Shared state storage
└── config/ # ConfigurationRelated MCP server: Claude Team MCP
Agents
Agent | Role | Capabilities |
Architect | Architecture planning | Project analysis, design patterns, tech stack decisions |
Developer | Code implementation | Task execution, code generation, permission workflow |
Reviewer | Code quality | Security checks, bug detection, code standards |
Tester | Quality assurance | Test planning, failure analysis, coverage estimation |
MCP Tools
list_files- List files in directoriesget_file_content- Read file contentscreate_task- Create tasks in shared queueupdate_task- Update task statussend_message- Agent-to-agent communicationget_messages- Retrieve messagesread_project_context- Analyze project structurereview_code- Static code analysis
Quick Start
# Install dependencies
pip install -r requirements.txt
# Run MCP server
python -m mcp_server.server
# Or with Docker
docker build -t agent-mcp .
docker run -p 8080:8080 agent-mcpIntegration
OpenCode MCP Config
{
"mcpServers": {
"agent-team": {
"command": "python",
"args": ["-m", "mcp_server.server"],
"cwd": "/path/to/agent-mcp"
}
}
}Kilo AI Connection
The MCP server exposes a stdio interface compatible with Kilo AI's MCP client for agent communication.
This server cannot be deployed
Maintenance
Related MCP Connectors
- ParleyOAuthdev.weldra
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Project management for AI agents: tasks, docs, decisions and time in one shared team context.
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
- OolkinOAuthcom.oolkin
AI colleagues that keep your standards, your project and their reasoning between sessions
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA reusable AI software development team built on MCP. 13 specialized agents (Project Manager, Backend, Frontend, QA, Security, DevOps, UX, and more) collaborate via shared SQLite state. Exposes 44 MCP tools across 12 domains. All discussions and decisions are stored in the database so agents get back up to speed immediately when re-loaded.MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that turns multiple AI coding agents into a coordinated team that chats, debates, remembers, audits security, and works in parallel on the same project.MIT
- FlicenseNot gradedqualityCmaintenanceEnables users to generate complete, production-ready software projects from simple ideas by coordinating 8 specialized AI agents through the Model Context Protocol.4-
- AlicenseNot gradedqualityDmaintenanceFacilitates autonomous AI agent collaboration on software projects through file-based task management and inter-agent communication via the Model Context Protocol.288 npmMIT