Elastica MCP Server
About
Efficient server implementation that leverages the Elastica Cosserat-Rod simulation framework to facilitate Model Context Protocol (MCP).
Details
- Author
- skim0119
- Downloads
- 126
- Categories
- Other
Jump to
- Run Elastica simulations via MCP
- Control simulation parameters remotely
- Monitor simulation state in real‑time
- Support for continuum snake models and other examples
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Elastica MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, run uv sync, then execute elastica_mcp_server. Add the server to your Claude Desktop’s mcp.json configuration under the key elastica-simulation-server.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"elastica mcp server": {
"elastica-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}
McpServers
{
"elastica-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
Elastica MCP Server
A Python-based Model Context Protocol (MCP) server for controlling Elastica soft slender-body physics simulations with natural language.
Features
- Run Elastica simulations through MCP
- Control simulation parameters remotely
- Monitor simulation state in real-time
- Support for various Elastica examples (including continuum snake models)
Requirements
- Python 3.10+
- PyElastica >= 0.3.3
- MCP
- uv (for source installation)
Launching the server
git clone https://github.com/skim0119/elastica-mcp-server.git
uv sync
elastica_mcp_server
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



