mcp-server-demo
by BooboNikita
Overview
An example project demonstrating how to build an MCP server and an intelligent client capable of automatic tool calling and multi-agent orchestration for compliance risk assessment, sales, and technical support.
Installation
python mcptools.pyEnvironment Variables
- KIMI_API_KEY
- KIMI_API_URL
- EMBEDDING_SERVICE_URL
- KIMI_MODEL
- TAVILY_API_KEY
Security Notes
The `database.py` file hardcodes MySQL root user credentials ('root', '123456') for a local database connection. This is a critical security vulnerability for anything beyond an isolated, ephemeral demo. The `subprocess.Popen` calls in `src/a2a/manager.py` are used for internal agent orchestration with fixed module names, posing a low risk of arbitrary command execution. Inter-service communication relies on fixed `localhost` ports without explicit authentication, which could be a risk if `localhost` network access is compromised. The `src/compliance_warning/service.py` attempts to 'auto-fix' LLM-generated JSON by replacing escaped quotes, which could lead to unexpected parsing or resource exhaustion if presented with a maliciously crafted payload.
Similar Servers
mcpstore
Orchestrate Microservice Context Protocol (MCP) services and adapt them for integration with various AI frameworks like LangChain, managing tools and their lifecycle.
agentor
Build and deploy scalable AI agents that can interact with various tools and communicate via A2A and MCP protocols.
Polymcp
A comprehensive TypeScript framework for building and orchestrating Model Context Protocol (MCP) servers and AI agents, enabling LLMs to intelligently discover, select, and execute external tools.
mcpc
Build and compose agentic Model Context Protocol (MCP) servers and tools, enabling AI assistants to discover, integrate, and orchestrate other MCP servers for complex tasks.