Skip to main content

Model Context Protocol server for Rowan computational chemistry platform

Project description

Rowan MCP Server

MCP server for making it easy to run Rowan's molecular design and simulation tools.


Installation

Option 1: Auto-Install (No manual installation needed!)

Just add this to your MCP configuration and it will automatically install and run:

HTTP/SSE configuration:

{
  "mcpServers": {
    "rowan": {
      "type": "http",
      "url": "http://127.0.0.1:6276/sse"
    }
  }
}

Then start the server:

# Set your API key
export ROWAN_API_KEY="your_api_key_here"

# Start the HTTP server
uvx --from rowan-mcp rowan-mcp

Option 2: Manual Installation

If you prefer to install the package first:

Using uv:

uv add rowan-mcp

Using pip:

pip install rowan-mcp

Then configure and start:

{
  "mcpServers": {
    "rowan": {
      "type": "http", 
      "url": "http://127.0.0.1:6276/sse"
    }
  }
}
# Set API key and start server
export ROWAN_API_KEY="your_api_key_here"
rowan-mcp

Get API Key

Visit labs.rowansci.com → Create account → Generate API key

Start Using

Ask your AI: "Calculate the pKa of aspirin" or "Optimize the geometry of caffeine"


What You Can Do

Ask the LLM to:

  • Calculate drug properties: "Predict drug-likeness of aspirin"
  • Optimize molecular structures: "Optimize the geometry of aspirin"
  • Predict chemical behavior: "What's the pKa of acetic acid?"
  • Run calculations: "Calculate the HOMO and LUMO of benzene"

System Requirements

  • Python 3.11+
  • Package manager: uv (recommended) or pip
  • Rowan API key (free at labs.rowansci.com)
  • MCP-compatible client (Claude Desktop, etc.)

Development commands (if you cloned the repo):

# Run from source
export ROWAN_API_KEY="your_api_key_here"
uv run python -m rowan_mcp

Available Tools

Total: 48 MCP Tools

  • 28 Dedicated Workflow Functions (all workflows from Rowan v2.1.9)
  • 1 Batch Workflow Function
  • 3 Molecule Lookup Tools
  • 10 Workflow Management Tools
  • 6 Protein Management Tools

Chemistry Calculations

  • submit_basic_calculation_workflow - Energy, optimization, frequencies with multiple engines (omol25, xtb, psi4)
  • submit_conformer_search_workflow - Conformational search with multiple search modes (rapid/careful/meticulous)
  • submit_conformers_workflow - Conformer generation and enumeration (different from conformer_search)
  • submit_multistage_opt_workflow - Multi-stage geometry optimization with sequential accuracy levels
  • submit_scan_workflow - Molecular scans (dihedral, bond, angle) with wavefront propagation
  • submit_irc_workflow - Intrinsic reaction coordinate calculations for transition states

Molecular Properties

  • submit_pka_workflow - Microscopic pKa calculations with customizable pH ranges and elements
  • submit_macropka_workflow - Macroscopic pKa calculations across pH and charge ranges
  • submit_solubility_workflow - Solubility predictions across multiple solvents and temperatures
  • submit_redox_potential_workflow - Electrochemical reduction/oxidation potentials
  • submit_descriptors_workflow - ML-ready molecular descriptors and features
  • submit_tautomer_search_workflow - Tautomer enumeration with reckless/rapid/careful modes
  • submit_admet_workflow - ADME/Tox property predictions for drug discovery
  • submit_hydrogen_bond_basicity_workflow - Hydrogen bond basicity (pKBHX) predictions

Reactivity Analysis

  • submit_fukui_workflow - Fukui indices for electrophilic/nucleophilic reactivity sites

Electronic Structure

  • submit_spin_states_workflow - Spin state energy calculations for different multiplicities

Spectroscopy & Analysis

  • submit_ion_mobility_workflow - Ion mobility mass spectrometry collision cross-section (CCS) predictions
  • submit_strain_workflow - Molecular strain energy calculations for rings and cages

Transition States & Reactions

  • submit_double_ended_ts_search_workflow - Transition state search from reactant and product structures
  • submit_pose_analysis_md_workflow - Molecular dynamics simulations on docked protein-ligand complexes

Protein & Drug Discovery

  • submit_docking_workflow - Protein-ligand docking with multiple executables (Vina, QVina2, Smina)
  • submit_batch_docking_workflow - High-throughput docking for virtual screening campaigns
  • submit_protein_cofolding_workflow - Multi-protein and protein-ligand cofolding predictions
  • submit_msa_workflow - Multiple sequence alignment for protein structure prediction

Batch Processing

  • batch_submit_workflow - Submit multiple molecules through any workflow type for high-throughput processing

Molecule Management

  • molecule_lookup - Convert molecule names, CAS numbers, IUPAC names to SMILES
  • batch_molecule_lookup - Bulk molecule name to SMILES conversion
  • validate_smiles - Validate and standardize SMILES strings

Protein Management

  • create_protein_from_pdb_id - Create protein from PDB ID (e.g., '1HCK')
  • retrieve_protein - Get protein data by UUID
  • list_proteins - List all available proteins
  • upload_protein - Upload custom protein structures
  • delete_protein - Remove protein from workspace
  • sanitize_protein - Clean and validate protein structures

Workflow Management

  • workflow_get_status - Check workflow status with detailed progress information
  • workflow_stop - Stop running workflows
  • workflow_delete - Remove workflows from workspace
  • retrieve_workflow - Get complete workflow data and results
  • retrieve_calculation_molecules - Extract molecular structures from calculations
  • list_workflows - List all workflows with filtering options
  • workflow_update - Modify workflow parameters
  • workflow_is_finished - Check if workflow is complete
  • workflow_delete_data - Remove workflow data while keeping metadata
  • workflow_fetch_latest - Get most recent workflow results

Requirements

  • Python 3.11+
  • Rowan API key
  • MCP-compatible AI assistant (Claude Desktop, etc.)

Recent Updates

Latest Fixes (November 2025)

  • Fixed double_ended_ts_search: Corrected Settings parameter structure (basis_set instead of basis)
  • Fixed spin_states: Now correctly extracts multiplicities from charge/multiplicity pairs
  • 🔧 Streamlined workflows: Removed workflows better suited for web interface (large data outputs, beta features)

All workflow implementations now match the exact Rowan API specification from the stjames-public repository.


Experimental: Desktop Extension (Work in Progress)

I'm developing a one-click desktop extension (.dxt) for Claude Desktop that eliminates command-line setup. This feature is currently being refined for optimal compatibility with the MCP extension system.

Current status: Installation workflow needs refinement for seamless user experience.

For now, we recommend using the standard Package Installation method above, which is fully tested and reliable.


Getting Help


Citation

If you use this MCP tool in your research, please cite the underlying Rowan platform:

Rowan Scientific. https://www.rowansci.com (accessed 2025-07-01).

For complete citation information including specific computational engines, methods, and workflows used in your calculations, please refer to Rowan's citation guidelines.


Publishing (Maintainer Notes)

To publish a new version to PyPI:

# Update version in pyproject.toml and rowan_mcp/__init__.py
# Build the package
uv build

# Publish to PyPI (requires API token)
uv publish

# Or publish to TestPyPI first
uv publish --index-url https://test.pypi.org/simple/

MCP inspector

# Start the server first
export ROWAN_API_KEY="your_api_key_here" 
uv run python -m rowan_mcp &

# Then inspect
npx @modelcontextprotocol/inspector http://127.0.0.1:6276/sse

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rowan_mcp-2.3.0.tar.gz (151.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rowan_mcp-2.3.0-py3-none-any.whl (74.4 kB view details)

Uploaded Python 3

File details

Details for the file rowan_mcp-2.3.0.tar.gz.

File metadata

  • Download URL: rowan_mcp-2.3.0.tar.gz
  • Upload date:
  • Size: 151.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.12

File hashes

Hashes for rowan_mcp-2.3.0.tar.gz
Algorithm Hash digest
SHA256 51734b438580aaab51912a9c0d347739283c5e4d0a342c8521065dc651e57b37
MD5 8265c5b553b62baaeaf5f657497582ae
BLAKE2b-256 e30bff0b29fcf00b03339dbd18433aaea390a81bc109576152c541bea0feca39

See more details on using hashes here.

File details

Details for the file rowan_mcp-2.3.0-py3-none-any.whl.

File metadata

  • Download URL: rowan_mcp-2.3.0-py3-none-any.whl
  • Upload date:
  • Size: 74.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.12

File hashes

Hashes for rowan_mcp-2.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9206e40142570958c7cce1e8e7e8ffea65d6c6b9a037248ff8f54777127765c3
MD5 9fdb41650e20b71b3d30ac74161ad74b
BLAKE2b-256 7e5bde5e375c634b64fefb65ba76269ddd739fb3a0f1e4e4b4dc952cddfdfa73

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page