BioMASS ODE Model Builder MCP server

MCP Bio-Modelling Servers

<!-- mcp-name: io.github.marcorusc/NeKo --> <!-- mcp-name: io.github.marcorusc/MaBoSS --> <!-- mcp-name: io.github.marcorusc/PhysiCell --> <!-- mcp-name: io.github.marcorusc/BioMASS -->

This package provides four stateful Model Context Protocol servers for mechanistic and systems-biology modelling:

All four servers use MCP over stdio and are distributed together as mcp-biomodelling-servers.

Publication

For more details, please check the related article:

"Intelligent tool orchestration for rapid mechanistic model prototyping: MCP servers as AI-biology interfaces"

Marco Ruscone, Miguel Vazquez & Alfonso Valencia, npj Systems Biology and Applications (2026)

https://doi.org/10.1038/s41540-026-00767-3

Requirements

automatically by pip or uvx.

• Python 3.10–3.14.
• MCP Python SDK 2.x, installed automatically with this package.
• The modelling-package dependencies declared in pyproject.toml, installed

package is not a replacement for the external dot renderer.

• The Graphviz system runtime for NeKo history diagrams. The Python graphviz

Check whether Graphviz is available with:

dot -V

If this command is missing, install Graphviz using your operating system or environment package manager. See the Graphviz installation guide for platform-specific instructions.

Installation

Install with pip

python -m pip install mcp-biomodelling-servers

The installation provides four console entry points:

mcp-neko-server
mcp-maboss-server
mcp-physicell-server
mcp-biomass-server

Run in an isolated environment with uvx

uvx --from mcp-biomodelling-servers mcp-neko-server
uvx --from mcp-biomodelling-servers mcp-maboss-server
uvx --from mcp-biomodelling-servers mcp-physicell-server
uvx --from mcp-biomodelling-servers mcp-biomass-server

Conda is optional. It remains useful when you want one explicitly managed environment for local development or additional native scientific software, but it is not required for the packaged entry points.

Configure an MCP client

The following example uses uvx and works with clients that accept the common mcp.json stdio configuration:

Shortened. The full README is on GitHub.