ContextBase (MCP Server)
@imfeniljikadara
ContextBase (MCP Server) について
A mcp server for storing and managing user context for ai apps via api
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is ContextBase (MCP Server)?
ContextBase (MCP Server) is a Model Context Protocol server for AI agents, assistants, and applications. It stores, retrieves, and manages per-user context using a simple API, built with TypeScript, Fastify, Prisma ORM, PostgreSQL, and Redis.
How to use ContextBase (MCP Server)?
Install Node.js v14+, PostgreSQL, and Redis. Clone the repository, install dependencies, configure environment variables (DATABASE_URL, REDIS_HOST, REDIS_PORT, JWT_SECRET, PORT), run database migrations with npx prisma migrate dev, then start the server with npm start or docker-compose up. Use the provided REST API endpoints (e.g., POST /api/auth/register, POST /api/memory) to register users, login, and manage memory objects.
Key features of ContextBase (MCP Server)
- Secure user authentication using JWT and bcrypt
- API endpoints for storing and retrieving memory data
- Comprehensive logging of user actions
- PostgreSQL for persistent storage
- Redis for high-performance caching
- Modern tech stack: TypeScript, Fastify, Prisma ORM
Use cases of ContextBase (MCP Server)
- AI assistants maintaining per-user conversation history
- Applications storing user-specific context across sessions
- Managing and retrieving user memories via a RESTful API
- Auditing user actions with a built-in logging system
FAQ from ContextBase (MCP Server)
What runtime and dependencies are required?
Node.js v14 or higher, PostgreSQL, and Redis are required. Docker and Docker Compose can be used for containerized deployment.
How does authentication work?
The server uses JWT and bcrypt. Users can register via POST /api/auth/register and login via POST /api/auth/login to obtain a token.
What data can be stored and retrieved?
Memory objects can be created, read, updated, and deleted via REST endpoints (/api/memory). Logs of user actions are accessible at /api/logs.
Where is data persisted?
Per-user context is stored in PostgreSQL; Redis is used as a caching layer for performance.
What transport protocol does the server use?
The server exposes a REST API over HTTP, listening on a configurable port (default 3000). No WebSocket or other transports are mentioned.
「その他」の他のコンテンツ
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Nginx UI
0xJackyYet another WebUI for Nginx
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Awesome Mlops
visengerA curated list of references for MLOps
コメント