MayaMCP
Verified Safeby MOK-5-ha
Overview
An AI Bartending Agent featuring a multi-turn conversational ordering system, RAG, tool calling, and text-to-speech capabilities.
Installation
mayamcpEnvironment Variables
- GEMINI_API_KEY
- CARTESIA_API_KEY
Security Notes
API keys are loaded from environment variables (.env file) and are not hardcoded. User input processing primarily relies on an LLM with predefined tools, which inherently limits direct code injection risks compared to `eval` or direct shell execution. The system downloads an avatar image via `requests.get`, which includes error handling. The `MemvidRetriever` uses `json.loads` on content it previously encoded, minimizing the risk of arbitrary code execution through JSON deserialization. No instances of `eval` or direct `subprocess.run` with untrusted input were identified.
Similar Servers
MaxKB
A powerful and easy-to-use enterprise-grade intelligent agent platform for RAG, complex workflow automation, and multi-model LLM integration.
Context-Engine
Context-Engine is a plug-and-play MCP retrieval stack that unifies code indexing, hybrid search, and optional LLM decoding, enabling product teams to ship context-aware agents and internal assistants for large or fast-changing codebases.
RagThisCode
Set up a RAG (Retrieval-Augmented Generation) system to chat with the code of any public or private GitHub repository.
agent-tool
A full-stack AI agent platform offering conversational AI with RAG, multi-LLM support, and extensible tooling via Model Context Protocol (MCP) servers.