pymol-cursor-mcp
Control PyMOL from Cursor via natural language. Enables describing molecular structures and styles in plain language to execute PyMOL commands through XML-RPC.
README
pymol-cursor-mcp - Truong Nguyen
Control PyMOL from Cursor via the Model Context Protocol (MCP). Describe structures and styles in plain language; the assistant calls PyMOL through XML‑RPC (run_command, run_python, pymol_get).
This project packages and documents a Cursor-first workflow. The same MCP server works with Claude Code if you prefer that CLI.
Upstream inspiration: nagarh/pymol-claude-code (PyMOL + MCP for Claude Code). This repo extends that idea with portable Cursor config, checks, scripts, and install docs.
Architecture
<p align="center"> <img src="flow.svg" alt="PyMOL MCP Cursor workflow — animated SVG" width="920"/> </p>
Same diagram style as upstream flow.svg, updated for Cursor (cyan node). Uses SVG/CSS animation (animateMotion, keyframes). If your Markdown preview looks static, open flow.svg directly on GitHub for the full motion.
What you get
| Piece | Purpose |
|---|---|
pymol_mcp_server.py |
MCP server (stdio) → PyMOL XML‑RPC |
.cursor/mcp.json |
Registers the pymol MCP server using ${workspaceFolder} |
.cursor/rules/*.mdc |
Agent hints for PyMOL tool usage |
scripts/start_pymol_for_mcp.sh |
Launch PyMOL with -R (macOS/Linux) |
verify_stack.py |
Sanity check: venv + MCP import + RPC to PyMOL |
examples/restore_pocket_labels.pml |
Example PyMOL script (labels / pocket) |
flow.svg |
Animated architecture diagram (same style as upstream repo) |
Quick install
git clone https://github.com/truong128/pymol-cursor-mcp.git
cd pymol-cursor-mcp
python3 -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -U pip
pip install -r requirements.txt
deactivate
Install PyMOL (conda‑forge recommended), then start RPC:
conda activate pymol_mcp # your env with pymol-open-source
pymol -R
Or: ./scripts/start_pymol_for_mcp.sh (after chmod +x).
In Cursor: Open Folder → this repo → Settings → MCP → confirm pymol connected → restart Cursor if needed.
python3 verify_stack.py
Should print: OK: MCP import + PyMOL RPC at http://localhost:9123
Full step-by-step: INSTALL.md
Daily use
- Terminal:
pymol -Ror VS Code/Cursor task: “PyMOL: start with XML-RPC”. - Cursor: Chat / Agent with this folder open.
- Prompt: e.g. “Fetch 1hvr, cartoon on protein, sticks on ligand.”
Summary of changes vs “Claude Code only” upstream
| Topic | Here |
|---|---|
| IDE | Cursor primary; .cursor/mcp.json, rules, tasks |
| RPC URL | PYMOL_RPC_URL env (default http://localhost:9123) |
| Paths | ${workspaceFolder} — clone anywhere |
| Windows | .cursor/mcp.json.windows.example |
| Verify | verify_stack.py |
| PyMOL start | scripts/start_pymol_for_mcp.sh + Run Task |
Troubleshooting
- MCP disconnected: see Cursor Output → MCP Logs; recreate
venv; reopen repo root as workspace. - PyMOL errors / missing
.dylib: install PyMOL from conda-forge into a dedicated env (see INSTALL.md). - Remote/HPC: run MCP where your editor runs; tunnel RPC (
PYMOL_RPC_URL, SSH-R) — details in INSTALL.md.
Credits
- PyMOL MCP idea and original server: pymol-claude-code — Hemant Nagar.
- Packaging and Cursor-focused docs: truong128. - Truong Nguyen
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.