Little_MCP
by ricard1406
Overview
A local AI assistant leveraging Retrieval-Augmented Generation (RAG) and multi-tool agent capabilities with Ollama for document Q&A and real-time information.
Installation
python mcp_server.pyEnvironment Variables
- OPENWEATHER_API_KEY
- DB_USER
- DB_PASSWORD
Security Notes
The `get_SQL_response` and `Update_SQL` functions in `mcp_server.py` are vulnerable to SQL injection. They directly use user-provided input (`l_operation`) as SQL queries via `cur.execute()` without any sanitization or parameterization. This allows an attacker to execute arbitrary SQL commands, potentially leading to data exfiltration, modification, or deletion, especially with `Update_SQL`.
Similar Servers
5ire
A sleek AI assistant client that integrates with various Large Language Models (LLMs) and utilizes Model Context Protocol (MCP) servers for advanced tools and prompts.
mcp-local-rag
A privacy-first document search server that runs entirely on your machine for semantic search of local documents.
rag-server-mcp
Provides Retrieval Augmented Generation (RAG) capabilities to Model Context Protocol (MCP) clients by indexing project documents and retrieving relevant content for LLMs.
SammelsuriumMCP
This server aggregates various information retrieval tools (web search, Wikipedia, local documents, calendar, weather) to enhance a local Small Language Model (SLM) with current and external data.