agent-tool
Verified Safeby DosiBridge
Overview
A full-stack AI agent platform integrating Retrieval Augmented Generation (RAG), multi-LLM support, and Model Context Protocol (MCP) for extensible tooling, offering a ChatGPT-like streaming interface for chat and document management.
Installation
docker-compose up -dEnvironment Variables
- NEXT_PUBLIC_API_BASE_URL
- DATABASE_URL
- CORS_ORIGINS
- OPENAI_API_KEY
- DEEPSEEK_KEY
- FIRECRAWL_API_KEY
- JWT_SECRET_KEY
- MCP_APIKEY_ENCRYPTION_KEY
- SUPERADMIN_EMAIL
- SUPERADMIN_PASSWORD
Security Notes
The system utilizes sandboxed 'eval' for mathematical expressions, which mitigates direct code injection risks but still requires careful review of the sandbox implementation. Hardcoded default credentials (e.g., '1234' for PostgreSQL, 'sparrow' for superadmin, and a placeholder for JWT_SECRET_KEY) are present in development configurations, which are explicitly marked for change in production. Secure key generation scripts (`generate_keys.py`) are provided to address this. Authentication is handled via JWT, and CORS is configurable, both contributing positively to security. Rate limiting is implemented to prevent abuse.
Similar Servers
MaxKB
An enterprise-grade agent platform for AI knowledge management, chatbot development, and complex AI workflow orchestration.
Context-Engine
A plug-and-play MCP retrieval stack for unifying code indexing, hybrid search, and optional LLM decoding to enable product teams to build context-aware AI agents for large or fast-changing codebases.
flexible-graphrag
The Flexible GraphRAG MCP Server provides a Model Context Protocol (MCP) interface for AI assistants (like Claude Desktop) to interact with a sophisticated RAG and GraphRAG system for document processing, knowledge graph auto-building, hybrid search, and AI Q&A.
mcp-local-rag
A privacy-first, local document search server that leverages semantic search for Model Context Protocol (MCP) clients.