MCP Agents: Model Context Protocol Examples

Discover 13 MCP projects that connect agents to external tools via the Model Context Protocol, integrating GitHub, databases, docs, and more.

The MCP Agents category contains 13 projects that demonstrate how to connect LLM agents to external tools and services using the Model Context Protocol (MCP). MCP provides a standardized way for agents to discover and invoke external functionality, such as querying databases, reading GitHub repositories, searching documentation, and interacting with productivity tools.

MCP Agent Projects

Project	Integration	Description
Doc-MCP	Docs, RAG	Semantic RAG documentation and Q&A system
LangGraph MCP Agent	Couchbase	LangChain ReAct agent with Couchbase integration
GitHub MCP Agent	GitHub	Repository insights and analysis via MCP
MCP Starter	GitHub	GitHub repository analyzer starter template
Talk to your Docs	Docs Q&A	Documentation Q&A agent with MCP
Database MCP Agent	GibsonAI	Conversational AI agent for managing database projects and schemas
Hotel Finder Agent	Hotel API	Hotel search and booking using MCP integration
Custom MCP Server	Custom	Custom MCP server implementation example
Couchbase MCP Server	Couchbase	Couchbase database integration with MCP protocol
ScaleKit Exa MCP Security	Security	Security-focused MCP integration with Exa search
Docker E2B MCP Agent	Docker, E2B	Secure AI agent running in sandboxed Docker environments via MCP Gateway
Taskade MCP Agent	Taskade	Workspace agent for managing projects, tasks, and workflows via Taskade MCP
Telemetry MCP Okahu	Okahu Cloud	Self-healing Text-to-SQL demo using Okahu Cloud traces via hosted MCP

Running an MCP Agent

Most MCP projects use a client-server architecture. The agent (client) connects to an MCP server that exposes tools the agent can call.

1. Navigate into the project

   cd mcp_ai_agents/<project_name>
   
2. Configure environment keys

   cp .env.example .env
   

   MCP projects usually require keys for both the LLM provider and the external service (e.g., GitHub token, Couchbase credentials, Exa API).

3. Install and run

   pip install -r requirements.txt
   python main.py
   

   Some projects also require starting the MCP server separately. Check the README for those instructions.

If you are new to MCP, start with the MCP Starter or Talk to your Docs projects. They clearly demonstrate how an agent discovers and calls tools through the MCP layer.