mcp-server-memory-tracker
Verified Safeby drkhannah
Overview
This server provides an agent-enabled memory system, allowing an MCP agent to save and retrieve information using OpenAI's vector store capabilities.
Installation
mcp run serverEnvironment Variables
- OPENAI_API_KEY
Security Notes
The server writes user-provided 'memory' directly to a temporary file and uploads it, and passes 'query' directly to OpenAI's search API. While there's no direct local code execution vulnerability, an attacker could potentially craft malicious inputs to exploit unforeseen vulnerabilities in OpenAI's file processing or search functionality.
Similar Servers
mem-agent-mcp
Provides a Model Context Protocol (MCP) server for a memory agent, enabling LLMs to interact with an Obsidian-like memory system for contextual assistance and RAG.
memorizer-v1
A .NET-based service for AI agents to store, retrieve, and search through memories using vector embeddings, featuring asynchronous chunking, version control, and relationship management.
mcp-duckdb-memory-server
Manages and queries a knowledge graph using DuckDB as an embedded backend for AI agent memory, specifically designed for the Model Context Protocol.
obsidian-mcp-server
Provides an OpenAI-compatible local Model Context Protocol (MCP) server within Obsidian, enabling external AI assistants and tools to semantically search the vault and perform file system operations.