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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。