ParaView MCP connects ParaView to LLM assistants through the Model Context Protocol, enabling execution of Python code and interaction with the ParaView GUI.
From the registry: Control ParaView through arbitrary Python code

Please install the `paraview-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **ParaView 6.0.1 with MCP plugin** — Download pre-built plugin binary from GitHub Releases for your platform (Linux x86_64 or macOS arm64) and load it in ParaView (https://github.com/failed33/paraview-mcp/releases/latest)
- **Start ParaView plugin server** — In ParaView: Tools > Manage Plugins > Load ParaViewMCP.so, then Tools > ParaView MCP > Start Server
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["paraview-mcp-server"]
- optional environment variables:
- `PARAVIEW_HOST`: Host where the ParaView plugin is listening (example: `127.0.0.1`)
- `PARAVIEW_PORT`: TCP port for the plugin bridge (example: `9877`)
- `PARAVIEW_AUTH_TOKEN`: Authentication token required for non-loopback connections (example: `<your-auth-token>`)
Note: 3 tools: execute_paraview_code (arbitrary Python in ParaView), get_pipeline_info, get_screenshot. Requires ParaView 6.0.1 GUI running with the MCP plugin. Connects via TCP bridge to the plugin.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.PARAVIEW_AUTH_TOKENrequiredAuthentication token (must match the plugin setting)