mcp-agent-starter-kit
Verified Safeby thusharanavod123
Overview
A starter kit for building custom AI agents using the Model Context Protocol (MCP) to connect real-world tools with Large Language Models (LLMs).
Installation
node mcp/server.jsEnvironment Variables
- OPENAI_API_KEY
- GEMINI_API_KEY
- CLAUDE_API_KEY
Security Notes
API keys are loaded from environment variables, not hardcoded. Dynamic tool loading is based on a fixed local directory, preventing path traversal via user input. The `mcp/server.js` directly uses `JSON.parse` on the request body without explicit error handling, which is a minor risk for malformed JSON, but generally acceptable for a starter kit. No `eval` or obvious malicious patterns found.
Similar Servers
mcp-use
Build AI agents and full-stack Model Context Protocol (MCP) servers with tools, resources, and interactive UI widgets in both Python and TypeScript.
claude-prompts-mcp
The Claude Prompts MCP Server provides hot-reloadable prompts, structured reasoning, and chain workflows to enhance AI assistant interactions.
agentor
A framework for building, prototyping, and deploying scalable AI Agents with integrated tools and support for MCP and A2A communication protocols.
mcpc
Build agentic Model Context Protocol (MCP) servers by composing existing MCP tools to create sophisticated AI agents capable of complex tasks.