mcp-skeleton
Verified Safeby deb-sahu
Overview
A generic template for building Model Context Protocol (MCP) servers to expose custom business logic as tools for AI models and clients.
Installation
docker run -d -p 8000:8000 -e LOG_LEVEL=INFO --name mcp-skeleton mcp-skeleton:latestEnvironment Variables
- SERVER_NAME
- SERVER_VERSION
- LOG_LEVEL
- MCP_SERVER_HOST
- MCP_SERVER_PORT
Security Notes
The server infrastructure (Docker, Kubernetes configurations, Pydantic settings) is robust. However, the `http_tools.py` example tool allows making arbitrary HTTP requests to any URL provided by the client. If deployed as-is and exposed to untrusted clients, this tool could be exploited for Server-Side Request Forgery (SSRF) attacks or internal network scanning. Developers are explicitly instructed to replace all example tools with their own, so the risk is contingent on proper implementation and security hardening of custom business logic.
Similar Servers
tmcp
A server implementation for the Model Context Protocol (MCP) to enable LLMs to access external context and tools.
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
mcp-servers
Provides an MCP server for Qdrant vector database integration, enabling AI agents to perform semantic search, store documents, and manage collections with advanced multi-tenant filtering capabilities.
mcp_server
This server template provides a foundation for building Model Context Protocol (MCP) servers to integrate with AI assistants and other MCP clients, offering tools for GitHub, Microsoft Graph, weather data, and JWT decoding.