Paraview_MCP
An autonomous agent that integrates large language models with ParaView for creating and manipulating scientific visualizations using natural language and visual inputs.
Paraview_MCP
ParaView-MCP is an autonomous agent that integrates multimodal large language models with ParaView through the Model Context Protocol, enabling users to create and manipulate scientific visualizations using natural language and visual inputs instead of complex commands or GUI operations. The system features visual feedback capabilities that allow it to observe the viewport and iteratively refine visualizations, making advanced visualization accessible to non-experts while augmenting expert workflows with intelligent automation.
Disclaimer
The current implementation of the connection between the MCP server and ParaView, in both the main and dev branches, relies on synchronization between pvserver and the ParaView client. Because this feature has been deprecated in most recent ParaView versions, the ParaView application view may not display content from the pvserver instance correctly, and overall stability issues may occur.
Video Demo
Click the image below to watch the video:
Installation
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] httpx
Setup for LLM
To set up integration with claude desktop, add the following to claude_desktop_config.json
"mcpServers": {
"ParaView": {
"command": "/path/to/python",
"args": [
"/path/to/paraview_mcp/paraview_mcp_server.py"
]
}
}
running
1. Start paraview server
python pvserver --multi-clients
2. Connect to paraview server from paraview GUI (file -> connect)
3. Start claude desktop app
Citing 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}
}
Authors
Paraview_MCP was created by Shusen Liu ([email protected]) and Haichao Miao ([email protected])
License
Paraview_MCP is distributed under the terms of the BSD-3 license.
LLNL-CODE-2007260
相关服务器
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Remote MCP Server (Authless)
A remote MCP server deployable on Cloudflare Workers, without authentication.
Node9-Proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
FLUX Image Generator
Generate images using Black Forest Lab's FLUX model.
Cookiecutter MCP UV Container
A Cookiecutter template for creating MCP servers with Apple container support and configurable transport methods.
MCP VSCode Cline
A guide for using the Cline VSCode extension to interact with Model Context Protocol (MCP) servers.
Google Workspace Developers
Developer documentation for Google Workspace APIs
OpenAPI Invoker
Invokes any OpenAPI specification through a Model Context Protocol (MCP) server.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
OpenZeppelin MCP Servers
Model Context Protocol Servers Repository for OpenZeppelin Products
