MCP-Server
by bautiroalt
Overview
A unified server for managing Model Context Protocols, integrating AI analytics (META-MINDS), file operations, real-time streaming, and monitoring with an admin panel and advanced security features.
Installation
docker-compose up -dEnvironment Variables
- JWT_SECRET_KEY
- API_KEY
- API_KEY_NAME
- CORS_ORIGINS
- ALLOWED_HOSTS
- DATA_DIRECTORY
- LOG_FILE
- REDIS_URL
- MONGO_URL
- DB_NAME
- ADMIN_USERNAME
- ADMIN_PASSWORD_HASH
- RATE_LIMIT_PER_MINUTE
- RATE_LIMIT_BURST
- MAX_FILE_SIZE
- ALLOWED_EXTENSIONS
- ENABLE_METRICS
- METRICS_PATH
- HEALTH_CHECK_PATH
- GRAFANA_PASSWORD
- MONGO_USERNAME
- MONGO_PASSWORD
- ENVIRONMENT
- META_MINDS_ENABLED
- META_MINDS_DEFAULT_QUESTIONS
- META_MINDS_QUALITY_THRESHOLD
- META_MINDS_REPORTS_DIR
- REACT_APP_BACKEND_URL
- REACT_APP_API_URL
- REACT_APP_MCP_API_URL
Security Notes
The server has critical security risks related to file system interaction. The MCP Tools (`read_file`, `write_file`, `list_directory`, `search_files`) and File Management API endpoints (`/files/{file_path:path}`) directly use user-provided paths without sufficient validation against directory traversal attacks (e.g., `../`). This could allow unauthorized access, modification, or deletion of arbitrary files outside intended data directories. Additionally, default admin credentials (`Jatin23K`, `#JK2025sy#`) are hardcoded in `backend/data/users/users.json`, which is a common vulnerability if not changed. The broad CORS policy (`Access-Control-Allow-Origin: *`) configured for development in `firebase.json` and potentially in `main.py` poses a risk if not restricted for production APIs. While some security measures like JWT authentication, bcrypt, rate limiting, and input sanitization methods are present in `security_manager.py`, their application is not consistently demonstrated or robust enough to mitigate direct file system access vulnerabilities.
Similar Servers
tmcp
A server implementation for the Model Context Protocol (MCP) to enable LLMs to access external context and tools.
SageMCP
A scalable platform for hosting MCP servers with multi-tenant support, OAuth integration, and connector plugins for various services, deployed on Kubernetes.
toolhive-cloud-ui
A UI for interacting with AI models via OpenRouter and managing/utilizing MCP (Model Context Protocol) servers and their tools from a centralized catalog.
agentxsuite
A unified open-source platform for connecting, managing, and monitoring AI agents and tools across various Model Context Protocol (MCP) servers.