ParaView-MCP
Paraview_MCP
ParaView-MCP 是一个自主智能体,通过模型上下文协议(Model Context Protocol)将多模态大语言模型与 ParaView 集成,使用户能够使用自然语言和视觉输入来创建和操作科学可视化,而无需复杂的命令或 GUI 操作。该系统具备视觉反馈功能,允许其观察视口并迭代优化可视化效果,使非专家也能进行高级可视化操作,同时通过智能自动化增强专家工作流。
免责声明
当前 MCP 服务器与 ParaView 之间的连接实现(在主分支和开发分支中)依赖于 pvserver 和 ParaView 客户端之间的同步。由于此功能在最近的大多数 ParaView 版本中已被弃用,ParaView 应用程序视图可能无法正确显示来自 pvserver 实例的内容,并可能出现整体稳定性问题。
Related MCP server: MCP LAMMPS Server
视频演示
点击下方图片观看视频:

安装
git clone https://github.com/LLNL/paraview_mcp.git
cd paraview_mcp
conda create -n paraview_mcp python=3.10
conda install conda-forge::paraview
conda install mcp[cli] httpxLLM 设置
要设置与 Claude Desktop 的集成,请将以下内容添加到 claude_desktop_config.json 中
"mcpServers": {
"ParaView": {
"command": "/path/to/python",
"args": [
"/path/to/paraview_mcp/paraview_mcp_server.py"
]
}
}运行
1. 启动 paraview 服务器
python pvserver --multi-clients2. 从 paraview GUI 连接到 paraview 服务器 (文件 -> 连接)
3. 启动 claude 桌面应用程序
引用 Paraview_MCP
S. Liu, H. Miao, and P.-T. Bremer, “Paraview-MCP: Autonomous Visualization Agents with Direct Tool Use,” in Proc. IEEE VIS 2025 Short Papers, 2025, pp. 00
@inproceedings{liu2025paraview,
title={Paraview-MCP: Autonomous Visualization Agents with Direct Tool Use},
author={Liu, S. and Miao, H. and Bremer, P.-T.},
booktitle={Proc. IEEE VIS 2025 Short Papers},
pages={00},
year={2025},
organization={IEEE}
}作者
Paraview_MCP 由 Shusen Liu (liu42@llnl.gov) 和 Haichao Miao (miao1@llnl.gov) 创建
许可证
Paraview_MCP 根据 BSD-3 许可证的条款分发。
LLNL-CODE-2007260
This server cannot be deployed
Maintenance
Related MCP Connectors
AI visual generation agent: multi-pipeline rendering, prompt crafting, and image composition.
Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
Design, save, and run outcome-aligned AI workflows and verifiers, with reliable image output.
Agent-Native design tool - create and edit visual designs with agent assistance
Related MCP Servers
AlicenseAqualityFmaintenanceGPU-accelerated graph visualization and analytics server for Large Language Models that integrates with Model Control Protocol (MCP), enabling AI assistants to visualize and analyze complex network data.176 npm11MIT- AlicenseNot gradedqualityFmaintenanceA Model Context Protocol server that enables AI assistants to interact with LAMMPS for molecular dynamics simulations through natural language commands.14Apache 2.0
- AlicenseBqualityCmaintenanceViznoir empowers AI agents to directly analyze and visualize complex 3D scientific and engineering data in cinematic resolution using a fully headless VTK engine. It enables LLMs to seamlessly execute advanced physical analysis, 3D rendering, and generate publication-ready animations purely through natural language commands.2318MIT
- AlicenseNot gradedqualityFmaintenanceIntegrates GROMACS molecular dynamics simulations with VMD visualization, enabling setup, execution, analysis, and 3D visualization of molecular dynamics workflows through natural language.23MIT