mcp-tools
Verified Safeby clerk
Overview
Facilitates the integration of Model Context Protocol (MCP) into AI applications, enabling secure, consent-based access to private user data via OAuth on both client and server sides.
Installation
No command providedEnvironment Variables
- CLERK_PUBLISHABLE_KEY
- CLERK_SECRET_KEY
- NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY
- REDIS_URL
- DATABASE_URL
- JWT_SECRET
Security Notes
The library employs standard OAuth and secure coding practices for handling authentication and data persistence. It relies on environment variables for sensitive keys and configurable persistent stores (Redis, Postgres, SQLite) for session data. `JSON.parse` is used for deserialization of internally stored data, which is generally safe within a controlled environment. The primary security considerations for implementers are the secure configuration and management of these persistent stores and API keys. No 'eval' or obvious malicious patterns were found in the provided source code.
Similar Servers
mcp-openapi-server
Exposes OpenAPI endpoints as Model Context Protocol (MCP) tools, enabling Large Language Models (LLMs) to discover and interact with REST APIs through a standardized protocol.
SageMCP
A scalable platform for hosting MCP servers with multi-tenant support, OAuth integration, and connector plugins for various services, deployed on Kubernetes.
mcp-server-playground
A Model Context Protocol (MCP) server that acts as an OAuth proxy for 3rd party authorization servers like Auth0, provides stateful session management, and exposes various tools for system time, streaming, project keyword searching, and AWS services (S3, ECS, CloudWatch Logs, Bedrock).
toolhive-cloud-ui
A Next.js application for visualizing Model Context Protocol (MCP) servers and facilitating their integration with AI agents.