LW MCP Agents

by Autumn-AIs

Integrations

  • Provides web search capabilities through Brave's search engine, allowing agents to retrieve information from the internet

🚀 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


📚 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.

A lightweight framework for building and orchestrating AI agents through the Model Context Protocol, enabling users to create scalable multi-agent systems using only configuration files.

  1. 🔍 Why Use LW MCP Agents?
    1. 🧠 What Can You Build?
      1. 🏗️ Architecture at a Glance
        1. 📚 Table of Contents
          1. 🚀 Getting Started
            1. 🔧 Installation
            2. ▶️ Run Your First Agent
            3. 🤖 Try a Multi-Agent Setup
            4. 🖥️ Claude Desktop Integration
          2. 📦 Example Agents
            1. ⚙️ Running Agents
              1. 🔹 Basic Command
              2. 🔸 Advanced Options
            2. 🛠️ Custom Agent Creation
              1. 🧱 Minimal Config
              2. 🧠 Adding Capabilities
              3. 🔄 Orchestrator Agent
            3. 🧬 How It Works
              1. 🧩 Capabilities as Reasoning Units
              2. 📖 Research Example
            4. 🧱 Technical Architecture
              1. 🧠 Key Components
              2. 🌐 Architecture Highlights
            5. 🙌 Acknowledgements

              Related MCP Servers

              • -
                security
                F
                license
                -
                quality
                A comprehensive suite of Model Context Protocol servers designed to extend AI agent Claude's capabilities with integrations for knowledge management, reasoning, advanced search, news access, and workspace tools.
                Last updated -
                5
                TypeScript
                • Apple
              • -
                security
                F
                license
                -
                quality
                A Model Context Protocol server that enables role-based context management for AI agents, allowing users to establish specific instructions, maintain partitioned memory, and adapt tone for different agent roles in their system.
                Last updated -
                TypeScript
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that allows AI assistants to interact with the Neuro-Symbolic Autonomy Framework, enabling capabilities like running NSAF evolution with customizable parameters and comparing different agent architectures.
                Last updated -
                Python
                MIT License
                • Apple
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that provides AI agents with secure access to local filesystem operations, enabling reading, writing, and managing files through a standardized interface.
                Last updated -
                14
                1
                TypeScript
                Apache 2.0

              View all related MCP servers

              ID: bepukxvwgc