Related MCP Server Resources

Explore more AI models, providers, and integration options:

  • Explore AI Models
  • Explore AI Providers
  • Explore MCP Servers
  • LangDB Pricing
  • Documentation
  • AI Industry Blog
  • MCP Atlassian
  • Claude MCP Server
  • Agent MCP
  • MCP Pokemon Server
  • Gemini MCP Image Generation Server
Back to MCP Servers
LW MCP Agents

LW MCP Agents

Public
Autumn-AIs/LW-MCP-agents

Lightweight, modular framework for building and orchestrating AI agents using Model Context Protocol, enabling scalable multi-agent collaboration, specialization, and task delegation through simple configuration files.

python
0 tools
May 29, 2025
Updated Jun 4, 2025

Supercharge Your AI with LW MCP Agents

MCP Server

Unlock the full potential of LW MCP Agents through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available โ€ข No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

๐Ÿš€ 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 reasonโ€”without writing complex orchestration logic.

Build scalable, composable AI systems using only configuration files.


๐Ÿ” Why Use LW MCP Agents?

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

๐Ÿง  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

๐Ÿ—๏ธ Architecture at a Glance

LW-MCP-agents-diagram


๐Ÿ“š Table of Contents

  • Getting Started
  • Example Agents
  • Running Agents
  • Custom Agent Creation
  • How It Works
  • Technical Architecture
  • Acknowledgements

๐Ÿš€ Getting Started

๐Ÿ”ง 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

โ–ถ๏ธ Run Your First Agent

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

๐Ÿค– 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.


๐Ÿ–ฅ๏ธ 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" } } } }

๐Ÿ“ฆ Example Agents

  • Base Agent
    A minimal agent that connects to tools via MCP.
    ๐Ÿ“ examples/base_agent/

  • Orchestrator + Researcher
    Demonstrates hierarchical delegation and capability sharing.
    ๐Ÿ“ examples/orchestrator_researcher/

๐Ÿ’ก Contribute your own example! Submit a PR or reach out to the maintainers.


โš™๏ธ Running Agents

๐Ÿ”น Basic Command

python src/agent/agent_runner.py --config

๐Ÿ”ธ Advanced Options

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

๐Ÿ› ๏ธ Custom Agent Creation

๐Ÿงฑ Minimal Config

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

๐Ÿง  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: {document_text}" } ]

๐Ÿ”„ Orchestrator Agent

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

๐Ÿงฌ How It Works

๐Ÿงฉ 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

๐Ÿ“– 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

๐Ÿงฑ Technical Architecture

๐Ÿง  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

๐ŸŒ 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

๐Ÿ™Œ Acknowledgements

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

Publicly Shared Threads0

Discover shared experiences

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!

Share your threads to help others
Related MCPs5
  • MCP Atlassian
    MCP Atlassian

    Model Context Protocol server enabling AI agents to seamlessly interact with Atlassian products like...

    Added May 30, 2025
  • Claude MCP Server
    Claude MCP Server

    Lightweight Model Context Protocol server enabling real-time web search integration with Claude AI u...

    Added May 30, 2025
  • Agent MCP
    Agent MCP

    A framework leveraging the Model Context Protocol for creating multi-agent AI systems with coordinat...

    Added May 30, 2025
  • MCP Pokemon Server
    MCP Pokemon Server

    An MCP server implementation enabling interaction with the PokeAPI to fetch dynamic Pokรฉmon data and...

    Added May 30, 2025
  • Gemini MCP Image Generation Server
    Gemini MCP Image Generation Server

    Provides image generation capabilities via Google's Gemini 2 API using the Model Context Protocol, e...

    1 tools
    Added May 30, 2025