Cmxflow
by b-shieldscommunityv0.4.0
1
cmxflow provides composable blocks for building cheminformatics workflows such as molecule preparation, similarity screening, scoring, and docking. It also supports Bayesian optimization of workflow parameters and exposes an MCP server for agents to build, run, optimize, manage, and visualize workflows.
From the registry: Composable, tunable cheminformatics workflows: library preparation, clustering, docking, and more.
Install & configure
Prerequisites
- requiredInstall cmxflowInstall the Python package that provides the MCP server command.
$ pip install cmxflow - optionalOptional: Install PyMOLRequired only if you want to use the `view_structures` MCP tool for 3D visualization.
$ conda install -c conda-forge pymol-open-source
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `cmxflow` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install cmxflow** — Install the Python package that provides the MCP server command. Run: `pip install cmxflow`
Optional prerequisites:
- Optional: Install PyMOL — Required only if you want to use the `view_structures` MCP tool for 3D visualization. Run: `conda install -c conda-forge pymol-open-source`
Canonical MCP server config (stdio transport):
- command: `cmxflow-mcp`
- args: []
Note: The README shows the MCP server being added with `claude mcp add cmxflow -- cmxflow-mcp`, which implies a stdio server launched via the `cmxflow-mcp` command. No environment variables are documented.
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.Note: The README shows the MCP server being added with `claude mcp add cmxflow -- cmxflow-mcp`, which implies a stdio server launched via the `cmxflow-mcp` command. No environment variables are documented.
Tools (5)
build_workflow
Builds a cheminformatics workflow from composable blocks.
run_workflow
Runs a workflow on input data.
optimize_workflow
Optimizes workflow parameters using Bayesian optimization.
manage_workflows
Manages saved or reusable workflows.
view_structures
Visualizes molecular structures in 3D, using PyMOL.
Prerequisites
- • Python 3.11+
Packages
cmxflow
pypiv0.4.0transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Jun 15, 2026
- Last commit
- Jun 15, 2026
- Registry name
- io.github.b-shields/cmxflow
Categories
Related Servers
Labelhead Artist Momentum
Trending hip-hop artist momentum scores across four cultural dimensions.
74.7k
PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
37.3k
Openmetadata Mcp
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
14.6k