- Explore MCP Servers
- MCP_agent
Mcp Agent
What is Mcp Agent
MCP_agent is a repository that provides a series of tutorials for developing intelligent agents using the HEPAI framework. It includes setup instructions and examples of agents that utilize tools like AMap and arXiv, along with integration into the OpenWebUI frontend.
Use cases
Use cases for MCP_agent include developing intelligent agents for navigation using AMap, retrieving and summarizing scientific literature from arXiv, and integrating with the OpenWebUI for enhanced user interaction with AI models.
How to use
To use MCP_agent, first set up your environment by installing miniconda and creating a Python environment. Then, install the HEPAI framework and configure the OpenWebUI frontend. After setting the necessary environment variables for large models, you can start the OpenWebUI server and access the intelligent agents.
Key features
Key features of MCP_agent include comprehensive setup instructions, example agents for specific tasks (like AMap and arXiv), and seamless integration with the OpenWebUI frontend, allowing for user-friendly interaction with intelligent agents.
Where to use
MCP_agent can be used in various fields such as AI development, research, and data analysis, particularly where intelligent agents can assist in automating tasks or providing insights from large datasets.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp Agent
MCP_agent is a repository that provides a series of tutorials for developing intelligent agents using the HEPAI framework. It includes setup instructions and examples of agents that utilize tools like AMap and arXiv, along with integration into the OpenWebUI frontend.
Use cases
Use cases for MCP_agent include developing intelligent agents for navigation using AMap, retrieving and summarizing scientific literature from arXiv, and integrating with the OpenWebUI for enhanced user interaction with AI models.
How to use
To use MCP_agent, first set up your environment by installing miniconda and creating a Python environment. Then, install the HEPAI framework and configure the OpenWebUI frontend. After setting the necessary environment variables for large models, you can start the OpenWebUI server and access the intelligent agents.
Key features
Key features of MCP_agent include comprehensive setup instructions, example agents for specific tasks (like AMap and arXiv), and seamless integration with the OpenWebUI frontend, allowing for user-friendly interaction with intelligent agents.
Where to use
MCP_agent can be used in various fields such as AI development, research, and data analysis, particularly where intelligent agents can assist in automating tasks or providing insights from large datasets.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
智能体开发系列教程
1.事先配置
- [x] 下载并安装 miniconda (或者其它喜欢的Python环境创建方式):
conda create -n hepai python=3.11 conda activate hepai
- [x] 安装hepai高能AI智能体框架:
pip install hepai -U
- [x] 配置OpenWebUI前端:
conda create -n openwebui python=3.11 conda activate openwebui pip install open-webui
- [x] 设置HuggingFace镜像:
将HuggingFace镜像:'HF_ENDPOINT '= 'https://hf-mirror.com'
加入到本地的环境。对于Linux系统,可以将其加入到~/.bashrc文件中:
export HF_ENDPOINT=https://hf-mirror.com
- [x] 启动OpenWebUI前端:
open-webui serve --port 8088
- [x] 在环境变量中设置大模型相关环境变量,这里以Linux系统为例,以HEPAI平台的大模型为变量值,但是适配任何OpenAI格式的大模型API调用,只需要更改相应的值即可:
export HEPAI_MODEL="hepai/deepseek-r1:671b" # 大模型名称,如"hepai/deepseek-r1:671b"
export HEPAI_API_KEY="Your_API_Key" # 大模型API Key
export HEPAI_API_URL="https://aiapi.ihep.ac.cn/apiv2" # 大模型API URL
智能体后端目录
amap 高德地图MCP工具调用智能体
具体见:amap/assistant_amaps.md
arXiv 科学文献MCP工具调用智能体
具体见:arXiv/assistant_arXiv.md
MCPO与OpenWebUI集成,作为前端大模型的访问工具
具体见:openwebui-mcpos/mcpo.md
DevTools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.