Skip to main content
Glama

LW MCP Agents

by Autumn-AIs

🚀 LW MCP Agents

LW MCP Agents is a lightweight, modular framework for building and orchestrating AI agents using the Model Context Protocol (MCP). It empowers you to rapidly design multi-agent systems where each agent can specialize, collaborate, delegate, and reason—without writing complex orchestration logic.

Build scalable, composable AI systems using only configuration files.


🔍 Why Use LW MCP Agents?

  • Plug-and-Play Agents: Launch intelligent agents with zero boilerplate using simple JSON configs.
  • Multi-Agent Orchestration: Chain agents together to solve complex tasks—no extra code required.
  • Share & Reuse: Distribute and run agent configurations across environments effortlessly.
  • MCP-Native: Seamlessly integrates with any MCP-compatible platform, including Claude Desktop.

🧠 What Can You Build?

  • Research agents that summarize documents or search the web
  • Orchestrators that delegate tasks to domain-specific agents
  • Systems that scale reasoning recursively and aggregate capabilities dynamically

🏗️ Architecture at a Glance

LW-MCP-agents-diagram


📚 Table of Contents


🚀 Getting Started

🔧 Installation

git clone https://github.com/Autumn-AIs/LW-MCP-agents.git cd LW-MCP-agents python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt

▶️ Run Your First Agent

python src/agent/agent_runner.py --config examples/base_agent/base_agent_config.json

🤖 Try a Multi-Agent Setup

Terminal 1 (Research Agent Server):

python src/agent/agent_runner.py --config examples/orchestrator_researcher/research_agent_config.json --server-mode

Terminal 2 (Orchestrator Agent):

python src/agent/agent_runner.py --config examples/orchestrator_researcher/master_orchestrator_config.json

Your orchestrator now intelligently delegates research tasks to the research agent.


🖥️ Claude Desktop Integration

Configure agents to run inside Claude Desktop:

1. Locate your Claude config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add your agent under mcpServers:

{ "mcpServers": { "research-agent": { "command": "/bin/bash", "args": ["-c", "/path/to/venv/bin/python /path/to/agent_runner.py --config=/path/to/agent_config.json --server-mode"], "env": { "PYTHONPATH": "/path/to/project", "PATH": "/path/to/venv/bin:/usr/local/bin:/usr/bin" } } } }

📦 Example Agents

  • Base Agent
    A minimal agent that connects to tools via MCP.
    📁 examples/base_agent/
  • Orchestrator + Researcher
    Demonstrates hierarchical delegation and capability sharing.
    📁 examples/orchestrator_researcher/

💡 Contribute your own example! Submit a PR or reach out to the maintainers.


⚙️ Running Agents

🔹 Basic Command

python src/agent/agent_runner.py --config <your_config.json>

🔸 Advanced Options

OptionDescription
--server-modeExposes the agent as an MCP server
--server-nameAssigns a custom MCP server name

🛠️ Custom Agent Creation

🧱 Minimal Config

{ "agent_name": "my-agent", "llm_provider": "groq", "llm_api_key": "YOUR_API_KEY", "server_mode": false }

🧠 Adding Capabilities

Define specialized functions the agent can reason over:

"capabilities": [ { "name": "summarize_document", "description": "Summarize a document in a concise way", "input_schema": { "type": "object", "properties": { "document_text": { "type": "string" }, "max_length": { "type": "integer", "default": 200 } }, "required": ["document_text"] }, "prompt_template": "Summarize the following document in {max_length} words:\n\n{document_text}" } ]

🔄 Orchestrator Agent

{ "agent_name": "master-orchestrator", "servers": { "research-agent": { "command": "python", "args": ["src/agent/agent_runner.py", "--config=research_agent_config.json", "--server-mode"] } } }

🧬 How It Works

🧩 Capabilities as Reasoning Units

Each capability:

  1. Fills in a prompt using provided arguments
  2. Executes internal reasoning using LLMs
  3. Uses tools or external agents
  4. Returns the result

📖 Research Example

[INFO] agent:master-orchestrator - Executing tool: research_topic [INFO] agent:research-agent - Using tool: brave_web_search [INFO] agent:research-agent - Finished capability: research_topic

🧱 Technical Architecture

🧠 Key Components

ComponentRole
AgentServerStarts, configures, and runs an agent
MCPServerWrapperWraps the agent to expose it over MCP
CapabilityRegistryLoads reasoning tasks from config
ToolRegistryDiscovers tools from other agents

🌐 Architecture Highlights

  • Hierarchical Design: Compose systems of agents with recursive reasoning
  • Delegated Capabilities: Agents delegate intelligently to peers
  • Tool Sharing: Tools available in one agent become accessible to others
  • Code-Free Composition: Create entire systems via configuration

🙌 Acknowledgements

This project draws inspiration from the brilliant work on mcp-agents by LastMile AI.

-
security - not tested
A
license - permissive license
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

通过模型上下文协议构建和协调 AI 代理的轻量级框架,使用户能够仅使用配置文件创建可扩展的多代理系统。

  1. 🔍 为什么要使用 LW MCP 代理?
    1. 🧠 您可以构建什么?
      1. 🏗️ 架构概览
        1. 📚 目录
          1. 🚀 入门
            1. 🔧 安装
            2. ▶️ 运行你的第一个代理
            3. 🤖 尝试多代理设置
            4. 🖥️ Claude 桌面集成
          2. 📦示例代理
            1. ⚙️ 运行代理
              1. 🔹基本命令
              2. 🔸 高级选项
            2. 🛠️ 自定义代理创建
              1. 🧱 最小配置
              2. 🧠 添加功能
              3. 🔄 Orchestrator 代理
            3. 🧬 工作原理
              1. 🧩 能力作为推理单元
              2. 📖 研究示例
            4. 🧱 技术架构
              1. 🧠 关键组件
              2. 🌐 架构亮点
            5. 🙌 致谢

              Related MCP Servers

              • -
                security
                A
                license
                -
                quality
                A FastAPI-based implementation of the Model Context Protocol that enables standardized interaction between AI models and development environments, making it easier for developers to integrate and manage AI tasks.
                Last updated -
                10
                MIT License
              • A
                security
                F
                license
                A
                quality
                A Model Context Protocol server that enables AI agents to generate, fetch, and manage UI components through natural language interactions.
                Last updated -
                3
                57
                5
              • -
                security
                A
                license
                -
                quality
                An open-source implementation of the Model Context Protocol (MCP) that bridges AI agents with enterprise systems, enabling secure access to real-world data and capabilities.
                Last updated -
                2
                Apache 2.0
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that enhances AI agents by providing deep semantic understanding of codebases, enabling more intelligent interactions through advanced code search and contextual awareness.
                Last updated -
                51
                MIT License
                • Apple

              View all related MCP servers

              MCP directory API

              We provide all the information about MCP servers via our MCP API.

              curl -X GET 'https://glama.ai/api/mcp/v1/servers/Autumn-AIs/LW-MCP-agents'

              If you have feedback or need assistance with the MCP directory API, please join our Discord server