Cognio
Verified Safeby 0xReLogic
Overview
Provides persistent semantic memory for AI assistants via Model Context Protocol (MCP), enabling semantic search, project organization, auto-tagging, and summarization of context.
Installation
docker-compose up -dEnvironment Variables
- API_KEY
- GROQ_API_KEY
- OPENAI_API_KEY
- AUTOTAG_ENABLED
- SUMMARIZATION_METHOD
- EMBED_MODEL
- EMBED_DEVICE
- HYBRID_ENABLED
- COGNIO_API_URL
Security Notes
Default CORS `allow_origins=["*"]` allows all origins, which is a significant security risk for production environments if not restricted. API key authentication is optional by default, making all endpoints publicly accessible unless `API_KEY` is configured. `execSync` is used in the MCP server but calls a trusted local script (`setup-clients.js`) with fixed arguments, posing a low risk in this context. SQL injection is prevented through parameterized queries. Stores data in SQLite, which does not provide encryption at rest by default.
Similar Servers
context-sync
Providing persistent memory and context synchronization for AI development across various tools and projects.
claude-conversation-memory-mcp
Provides long-term memory for AI coding assistants by indexing conversation history with semantic search, decision tracking, and cross-project search.
memory-mcp
This MCP server provides memory storage and intelligent context window caching capabilities for Large Language Model (LLM) conversations, including archiving, retrieval, and summarization.
Simple-Memory-Extension-MCP-Server
A persistent key-value memory store for AI agents, designed to extend context windows and enable semantic search over stored memories.