AgentChat
by Shy2593666979
Overview
An AI Agent platform for building, deploying, and managing AI assistants that integrate various tools, Large Language Models (LLMs), knowledge bases (RAG), and Model Context Protocol (MCP) servers.
Installation
cd docker && ./start.shEnvironment Variables
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- JWT_SECRET_KEY
- MYSQL_PASSWORD
- MYSQL_ENDPOINT
- REDIS_ENDPOINT
- ALIYUN_OSS_ACCESS_KEY_ID
- ALIYUN_OSS_ACCESS_KEY_SECRET
- TAVILY_API_KEY
- WEATHER_API_KEY
- DELIVERY_API_KEY
- WECHAT_APP_ID
- WECHAT_SECRET
- WECHAT_TOKEN
- LANGFUSE_PUBLIC_KEY
- LANGFUSE_SECRET_KEY
Security Notes
Critical vulnerability due to `exec()` of potentially user-controlled Python code for custom agents (`src/backend/agentchat/services/autobuild/client.py`) without clear sandboxing mechanisms. High risk from a hardcoded default JWT secret (`src/backend/agentchat/api/JWT.py`) and various default API keys in `config.yaml` (e.g., AMap, Tavily, Alibaba Cloud Delivery, various LLMs) that could be active if not overridden. The use of MD5 hashing for passwords (`src/backend/agentchat/api/services/user.py`) is insecure. Command execution via `subprocess.run` for the `convert_to_pdf` tool is present, though its current usage appears constrained.
Similar Servers
mcpstore
Orchestrate Microservice Context Protocol (MCP) services and adapt them for integration with various AI frameworks like LangChain, managing tools and their lifecycle.
agentor
Build and deploy scalable AI agents that can interact with various tools and communicate via A2A and MCP protocols.
mcpc
Build and compose agentic Model Context Protocol (MCP) servers and tools, enabling AI assistants to discover, integrate, and orchestrate other MCP servers for complex tasks.
MCP-Agent
An autonomous AI agent designed to discover, connect to, and utilize tools and resources from various Model Context Protocol (MCP) servers to accomplish tasks.