Origin Pro MCP Server

An MCP (Model Context Protocol) server that enables AI assistants like Claude to control OriginLab Origin Pro via COM automation. All operations are reflected in Origin's GUI in real-time — you watch as the AI creates worksheets, plots graphs, and styles figures.

What Can It Do?

• Worksheet Management — Create workbooks, read/write data, import CSV/Excel, export CSV, column formulas, sort, transpose
• Matrices & 3D — Matrix books, XYZ gridding, 3D surface/scatter, contour, heatmap, image plots
• Graph Creation — Scatter, line, line+symbol, column, bar, area, pie, histogram, contour plots
• Graph Layers & Axes — Log scales, dual Y axis, panels, reference lines, text annotations
• Plot Styling — Colors, symbols, line width, publication-ready formatting in one call
• Analysis — Curve fitting, FFT, smoothing, integration, differentiation, interpolation, peak finding
• Statistics — Descriptive stats, two-sample t-test, frequency counts
• Project Management — New/save/load projects, export all graphs (with pixel-size control)
• LabTalk Scripting — Direct LabTalk execution with destructive/file-overwrite commands blocked

This MCP server is intentionally Windows-runtime-only. The AI agent or MCP client can run from Windows or WSL, but the MCP server process that talks to Origin must be launched with Windows Python and pywin32. WSL/Linux can edit the project and run non-COM unit tests, but cannot directly control Origin COM.

Quick Start

Agentic Setup (read this if you are an AI agent configuring this server)

Copy-paste rules to self-configure the origin-pro MCP with zero human steps:

1. Environment requirement. This server only works on Windows with a licensed Origin/OriginPro install and Windows Python with `pywin32`. COM automation cannot run from WSL or Linux Python. If the agent runs in WSL, it must launch the Windows executable (uvx.exe / Windows origin-pro-mcp), never WSL Python.
2. Preferred install path. Use uvx (zero setup) or pip install origin-pro-mcp. Both install to a Windows-local location and "just work":

   { "mcpServers": { "origin-pro": { "command": "uvx", "args": ["--quiet", "origin-pro-mcp"] } } }

From WSL, call uvx.exe instead of uvx (see Option A below).

1. Critical UNC rule. If you point at a local checkout from WSL, the repo MUST live under a Windows drive (e.g. C:\Users\YOU\Origin-Pro-MCP). Never reference it through a \\wsl.localhost\... UNC path: the background daemon (python -m origin_pro_mcp.daemon) cannot resolve a -m module or a working directory over UNC, so it fails silently (Origin never opens). uvx/pip install avoid this entirely.
2. Discover skills first. After connecting, call the `list_skills` tool to see bundled skills (e.g. publication-figure) and when to use each, then `get_skill(name)` to load the full step-by-step instructions before producing figures/plots/analysis. No file copying is needed — skills ship inside the package and are exposed by the server.

1. Prerequisites

• Windows with a licensed Origin/OriginPro installation that exposes the Automation Server
• Python 3.10+ (Windows Python, not WSL)

Tested environment: Origin Pro 2020. Other Origin/OriginPro versions may work if they expose compatible COM Automation Server and LabTalk behavior, but they are not verified by this project yet.

2. Install & Configure

Option A: uvx (recommended — zero setup)

No manual install needed. The MCP client launches the server for you. Just add this to your Claude Code MCP settings when Claude Code is running on Windows:

{
  "mcpServers": {
    "origin-pro": {
      "command": "uvx",
      "args": ["--quiet", "origin-pro-mcp"]
    }
  }
}

uvx automatically downloads and runs the server in an isolated environment. Nothing else to install. The --quiet flag keeps first-run dependency messages out of your MCP client logs.

If Claude Code or another MCP client is running inside WSL, launch the same Windows server by calling Windows uvx.exe directly:

{
  "mcpServers": {
    "origin-pro": {
      "command": "uvx.exe",
      "args": ["--quiet", "origin-pro-mcp"]
    }
  }
}

For a local checkout before publishing/installing, point Windows uvx at the Windows path of the repo:

{
  "mcpServers": {
    "origin-pro": {
      "command": "uvx.exe",
      "args": ["--quiet", "--refresh", "--from", "D:\\04.Agent OS\\Origin-Pro-MCP", "origin-pro-mcp"]
    }
  }
}

Keep the command and args as separate JSON array entries. That avoids quoting problems when a Windows path contains spaces. If WSL cannot find uvx.exe, set command to the full WSL path for the Windows executable, for example /mnt/c/Users/YOU/.local/bin/uvx.exe.

WSL users — the package must live on a Windows-local path, not a `\\wsl.localhost\...` (UNC) path. The server runs a background daemon (python -m origin_pro_mcp.daemon); Windows cannot resolve a -m module or use a working directory over a UNC path, so launching it from a WSL-filesystem checkout fails silently (Origin never opens and a console window flashes). uvx/pip install already install to a Windows-local location, so they are unaffected. If you point at a local checkout, clone it under a Windows drive (e.g. C:\Users\YOU\Origin-Pro-MCP) and reference that path — do not point the MCP config at a repo inside the WSL filesystem.

Option B: pip install from PyPI

pip install origin-pro-mcp

Then configure Claude Code:

{
  "mcpServers": {
    "origin-pro": {
      "command": "origin-pro-mcp"
    }
  }
}

Option C: Clone and run directly

git clone https://github.com/youngminsw/Origin-Pro-MCP.git
cd Origin-Pro-MCP
pip install -e .

{
  "mcpServers": {
    "origin-pro": {
      "command": "origin-pro-mcp"
    }
  }
}

Note: If Claude Code runs in WSL, make sure the uvx or python command points to your Windows Python, not WSL Python. Origin COM only works from Windows.

3. Origin Startup

You do not need to start Python or Origin manually. The MCP client starts origin-pro-mcp, which launches an isolated Origin instance for the session. By default the Origin window is visible, so you watch the agent create worksheets and plot graphs in real time.

Display mode — set the ORIGIN_PRO_MCP_VISIBLE environment variable in your MCP config:

{ "mcpServers": { "origin-pro": {
  "command": "origin-pro-mcp",
  "env": { "ORIGIN_PRO_MCP_VISIBLE": "0" }
} } }

4. Use It

Just ask Claude to work with Origin:

"Create a scatter plot from this data: x=[1,2,3,4,5], y=[2.1,4.0,5.9,8.1,10.0]"
"Apply publication styling to Fig1 with axis labels Temperature (K) and Absorbance (a.u.)"
"Fit a Gaussian to the data in Book1"
"Export all graphs to C:\Users\me\figures\"

File paths can be Windows style (C:\Users\me\fig.png) or WSL style (/mnt/c/Users/me/fig.png) — the server converts WSL paths automatically, so agents running in WSL can pass their native paths.

Agent Location vs Server Runtime

The agent does not have to run on Windows. These setups are valid:

• Windows agent -> Windows origin-pro-mcp server -> Origin Pro
• WSL agent -> Windows origin-pro-mcp server -> Origin Pro

The unsupported setup is WSL/Linux origin-pro-mcp server -> Origin Pro, because COM is a Windows API.

Version Support

This project is currently verified only with Origin Pro 2020. The implementation uses Origin's COM Automation Server and LabTalk, which exist across multiple Origin releases, so other versions may work. Treat them as unverified until someone runs the test suite and a real graph/export smoke test on that version.

Direct LabTalk Safety

The run_labtalk tool is available by default for styling, analysis, graph tweaks, and other advanced Origin operations. It blocks common destructive or file-writing LabTalk commands such as project reset, delete, save/open, file dialogs, external script execution, and graph export. Use the typed tools for saving, loading, importing, and exporting.

This is an accident-prevention guard, not a security sandbox for untrusted code.

Architecture

Claude Code (WSL or Windows)
    |  stdio (MCP protocol)
    v
MCP Server (Windows Python + win32com)
    |  COM automation
    v
Origin Pro (GUI visible in real-time)

Direct CLI (no MCP client)

Every MCP tool is also a plain command, so the repo alone can drive Origin — no MCP client, no per-task scripts. Same Windows-runtime rule applies (Windows Python + pywin32 + Origin).

# List all tools with their arguments
python -m origin_pro_mcp.cli list

# Call any tool: simple flags...
python -m origin_pro_mcp.cli list_worksheets
python -m origin_pro_mcp.cli apply_publication_style --graph_name Fig1

# ...or --json for values with spaces/paths (recommended for scripting)
python -m origin_pro_mcp.cli apply_publication_style --json '{"graph_name": "Fig1", "x_label": "Temperature (K)"}'
python -m origin_pro_mcp.cli export_graph --json '{"graph_name": "Fig1", "file_path": "/mnt/c/Users/me/fig1.png"}'

After pip install (or via uvx) the same is available as the origin-pro-cli command, e.g. origin-pro-cli list_worksheets.

Running a WSL agent? Invoke Windows Python with the package on the path, for example from the repo's src/ directory:

cd src && /mnt/c/.../python.exe -m origin_pro_mcp.cli list_worksheets

The CLI reflects over the same tool registry as the MCP server, so it always exposes exactly the tools listed below.

Available Tools (56 total)

Project Management

Worksheet Data

Matrix

Graphing

export_graph uses Origin's clipboard copy (size follows the page setup). export_graph_sized uses expGraph for direct pixel control.

Styling

Analysis

Statistics

Advanced

Example: Publication-Quality Figure

# 1. Start fresh
new_project()

# 2. Create data
create_worksheet(book_name="Data")
set_worksheet_data(
    book_name="Data", sheet_name="Sheet1",
    columns="[[300,350,400,450,500,550,600],[0.12,0.35,0.89,1.62,1.95,1.92,1.25],[0.08,0.22,0.62,1.35,1.88,1.90,1.12]]",
    column_names="Temperature,Pristine,Annealed"
)

# 3. Create line+symbol graph
create_graph(graph_name="Fig1", data_book="Data", data_sheet="Sheet1",
             x_col=1, y_col=2, plot_type="line+symbol")
add_plot_to_graph(graph_name="Fig1", data_book="Data", data_sheet="Sheet1",
                  x_col=1, y_col=3, plot_type="line+symbol")

# 4. One call does everything: colors, fonts, ticks, frame, legend
apply_publication_style(
    graph_name="Fig1",
    x_label="Temperature (K)",
    y_label="Absorbance (a.u.)",
    x_min=280, x_max=620, y_min=0, y_max=2.2,
    legend_entries="Pristine,Annealed",
    legend_position="top-right"
)

# 5. Export
export_graph(graph_name="Fig1", file_path="C:\\Users\\me\\fig1.png")

Result: A publication-ready figure with bold Arial labels, colorblind-safe colors (blue circles + red triangles), filled symbols, solid lines, inward ticks, closed frame, and positioned legend.

Claude Code Skill: Publication Figure

This server ships a bundled skill (src/origin_pro_mcp/skills/publication-figure.md) that teaches Claude how to create journal-quality figures step by step. No manual copying is needed — the skill is packaged inside the wheel and exposed over MCP, so any connecting agent discovers it automatically:

1. Call the `list_skills` tool — it returns each skill's name, title, and when to use it (e.g. publication-figure).
2. Call `get_skill("publication-figure")` to load the full markdown instructions.
3. Each skill is also available as an MCP resource at skill://<name> (e.g. skill://publication-figure) for clients that browse resources.

When you ask Claude to "make a publication figure", it can autonomously pull this skill and follow its workflow:

• Ask about data source, figure type, target journal
• Use colorblind-safe color palette (blue → red → green → orange → purple → cyan)
• Apply proper typography (Arial, bold, correct sizes)
• Follow a pre-export checklist

The skill also documents COM quirks observed while testing on Origin Pro 2020 — what works, what doesn't, and tested workarounds. This is invaluable if you need to customize beyond apply_publication_style.

Customizing the Skill for Your Style

The included skill is a generic starting template for paper-grade Origin figures. You should copy and customize it to match your lab's habits, target journals, and visual taste:

• Font: Change from Arial to your journal's preferred font (e.g., Helvetica, Times New Roman)
• Font sizes: Adjust axis title/tick label/legend sizes to match your journal's figure guidelines
• Color palette: Replace the default colorblind-safe palette with your group's standard colors
• Default export path: Set to your working directory
• Figure recipes: Add templates for your common figure types (XRD patterns, IV curves, etc.)
• Journal presets: Add specific formatting rules for your target journals (Nature, ACS, RSC, etc.)

Pull the skill with get_skill("publication-figure") (or copy src/origin_pro_mcp/skills/publication-figure.md) into your project and edit freely — it's meant to be a starting point, not a rigid template.

Key Origin Pro 2020 COM Quirks (documented in skill)

Supported Plot Types

Matrix plots (surface, contour, heatmap, image) come from a matrix via create_matrix_plot.

Supported Fitting Functions

curve_fit returns the fitted parameter values with standard errors plus R², SSR, reduced χ², and DoF. Exception: power fits and draws the curve, but Origin 2020 does not expose its parameter values over COM, so only the statistics are returned. Use list_fitting_functions to see the parameter names for each function.

Color Palette

apply_publication_style uses a muted pastel palette (no pure primaries — easier on the eyes, survives grayscale printing, colorblind-distinguishable):

Error bars automatically match their data series color. The fit curve drawn by curve_fit(plot_on_graph=...) uses a muted brick red (170, 68, 80).

Tip: Never use red + green as the only two colors — colorblind users cannot distinguish them.

Troubleshooting

License

MIT