FLASK-tools
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FLASK-toolsPredict the density of CCO"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FLASK-tools
Installation
To install the package, clone the repository and run:
pip install -e .
flask-tools-install --extras allOr install directly from GitHub:
pip install git+https://github.com/FLASK-LLNL/FLASK-tools.git
flask-tools-install --git-tag main --extras allExemplar FLASK-tools MCP servers
Here is a collection of commonly used MCP servers in the FLASK-copilot framework.
molecular_generation_server.py
retrosynthesis_reaction_server.py
SMILES.py
SMARTS_reactions.py
FLASKv2_reactions.py
get_chemprop2_pred.py
molecule_pricer.py
Using Chemprop tools (calculate_property_hf)
Related MCP server: MoziChem-MCP
Installation
1.) Installing the ChARGe package with the [chemprop] or [all] options to use the Chemprop MPNN models.
2.) Set Chemprop model checkpoint path as environment variable
export CHEMPROP_BASE_PATH=<LC_PATH_TO_CHEMPROP_MODELS>Testing Chemprop Installation
from charge.servers.molecular_property_utils import calculate_property_hf
property='density'
calculate_property_hf('COC(=O)COC=O','density')Expected Result:
[[1.3979296684265137]]Usage
The property input variable in calculate_property_hf must be set to one of the below properties.
valid_properties = {'density', 'hof', 'alpha','cv','gap','homo','lumo','mu','r2','zpve','lipo'}Using Chemprice tools
Installation
After installing the ChARGe package, run the additional commands to use the Chemprice tools (getting the commercial price of a SMILES string).
1.) Install chemprice with pip.
pip3 install --no-deps chemprice2.) Set API key for Chemspace as an environment variable
export CHEMSPACE_API_KEY=<ENTER_YOUR_CHEMSPACE_API_KEY>Testing Chemprice Installation
from charge.servers.molecular_property_utils import get_molecule_price
smiles='CCO'
get_molecule_price(smiles)Expected Result:
0.1056License
Copyright (c) 2025-2026, Lawrence Livermore National Security, LLC. and Binghamton University.
Produced at the Lawrence Livermore National Laboratory and Binghamton University.
SPDX-License-Identifier: Apache-2.0
LLNL-CODE-2006345
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Find and call the right MCP server for any task - pay per use, no install.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides chemical informatics endpoints for converting between chemical names and SMILES, processing molecule structures, and comparing molecules, with MCP compatibility.5MIT
- AlicenseNot gradedqualityDmaintenanceA collection of MCP servers for chemical engineering and chemistry applications, enabling AI assistants to perform thermodynamic calculations, equation of state modeling, and phase equilibrium computations.MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives LLMs native access to cheminformatics and molecular ML tools, enabling molecular structure manipulation, descriptor calculation, ML model training, and analysis report generation through natural conversation.32MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for Ketcher chemical structure editor integration, enabling SMILES/MOL/InChI conversion, image generation, molecular property calculation, and validation.MIT