failed33 avatar

ParaView MCP Server

failed33/paraview-mcp

Bridges ParaView's scientific visualization environment to LLM assistants by running a C++/Qt plugin inside ParaView itself, exposing a TCP socket that the Python MCP server connects to. The key tool is execute_paraview_code, which runs arbitrary Python in the active ParaView session, giving agents the same scripting access a human would have. You also get get_pipeline_info for inspecting the current visualization pipeline as JSON and get_screenshot to capture renders. Reach for this when you want an AI to automate complex ParaView workflows, generate visualizations from data programmatically, or interactively build and modify pipelines without clicking through menus. Requires ParaView 6.0.1 with the companion plugin loaded and listening on localhost:9877 by default.

GitHub stars
5
tools
3
transport
STDIO
last updated
Oct 26, 2026

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

execute_paraview_codeExecute Python code inside the active ParaView session

Execute Python code inside the active ParaView session

No parameter schema in public metadata yet.

get_pipeline_infoReturn a JSON snapshot of the current pipeline

Return a JSON snapshot of the current pipeline

No parameter schema in public metadata yet.

get_screenshotCapture the active render view as a PNG image

Capture the active render view as a PNG image

No parameter schema in public metadata yet.

Sponsors

Readme

ParaView MCP

ParaView MCP

CI PyPI CodeQL codecov License: MIT

Connect ParaView to LLM assistants through the Model Context Protocol.

The Python server is built with FastMCP 3.x. Support for the 2026-07-28 MCP specification is planned once FastMCP 4 reaches a stable release.

paraview-mcp-server has two runtime parts:


View the full README on GitHub

Details

Repository
github.com/failed33/paraview-mcp
Package
paraview-mcp-server
Transport
STDIO
Registry
MCP registry, active