# Originlab Mcp

> MCP Server for OriginLab Control OriginLab with natural language through AI clients via the Model Context Protocol.

- **Type:** MCP server
- **Install:** `agentstack add mcp-garethbeaumo-originlab-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [garethbeaumo](https://agentstack.voostack.com/s/garethbeaumo)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [garethbeaumo](https://github.com/garethbeaumo)
- **Source:** https://github.com/garethbeaumo/originlab-mcp

## Install

```sh
agentstack add mcp-garethbeaumo-originlab-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

OriginLab MCP Server
  
    Use AI as your OriginLab assistant
  
  
    Connect OriginLab data analysis and visualization to Antigravity, Claude, Cursor, and other AI clients through the Model Context Protocol.
  
  
    
    
    
    
    
  
  
    Quick Start · Features · Examples · Client Configuration
  
  
    简体中文 · English
  

> [!WARNING]
> **Early v0.2 release** - this project is still under active development. Features and APIs may change. It is suitable for testing and feedback, but not recommended for production use yet.

---

## What Is OriginLab MCP Server?

OriginLab MCP Server is a bridge between AI clients and OriginLab. It lets you import data, create plots, customize figures, run analysis, and export results through natural-language requests instead of manually operating the Origin UI.

```text
User: Import experiment.csv from my desktop into Origin, use the first column as X
      and the second column as Y, create a scatter plot, run a Gaussian fit,
      then export the graph as PNG.

AI: Done.
    Imported experiment.csv -> Sheet1 (200 rows x 5 columns)
    Created scatter plot -> Graph1
    Gaussian fit completed -> xc=2.35, w=0.82, A=156.3, R²=0.9987
    Exported -> C:\Users\Desktop\Graph1.png
```

### How It Works

```text
AI Client (Antigravity / Claude / Cursor)
       ↓ MCP over stdio
OriginLab MCP Server (Python)
       ↓ originpro + COM
OriginLab
```

## Requirements

| Requirement | Details |
| :--- | :--- |
| Operating system | Windows |
| OriginLab | OriginLab 2021 or later with a valid license |
| Python | 3.10+ |

## Quick Start

For AI assistants or one-command local setup, run this from the repository root:

```powershell
powershell -ExecutionPolicy Bypass -File .\scripts\install-and-open.ps1
```

The script installs `uv` if needed, runs `uv sync`, starts the local status panel, and opens `http://127.0.0.1:8765/` automatically. From that page you can test Origin and write MCP client configs.

Choose one installation method.

Option A: uv (recommended)

**1. Install uv**

```powershell
irm https://astral.sh/uv/install.ps1 | iex
```

**2. Install dependencies**

```powershell
cd C:\path\to\originlab-mcp
uv sync
```

**3. Start the server**

```powershell
uv run originlab-mcp
```

Option B: pip

**1. Create a virtual environment (optional but recommended)**

```powershell
cd C:\path\to\originlab-mcp
python -m venv .venv
.venv\Scripts\activate
```

**2. Install the project**

```powershell
pip install -e .
```

**3. Start the server**

```powershell
originlab-mcp
```

After startup, the server waits for MCP client requests over stdio. The first tool call automatically connects to the local OriginLab installation.

### Optional: Local Status Panel

To check whether the MCP server can start, whether Origin can be reached, and whether common client config files exist, start the local UI:

```powershell
uv run originlab-mcp-ui
```

Then open `http://127.0.0.1:8765/`. This page can start/stop a debug MCP server subprocess, test the Origin connection, and write the `originlab` MCP configuration for Antigravity / Gemini, Cursor, Codex, Trae, and Claude Desktop. For normal use, the AI client should still start the server automatically from its configuration.

When updating an existing config file, the UI creates a `.bak-timestamp` backup first. To prevent the browser from opening automatically:

```powershell
$env:ORIGINLAB_MCP_UI_NO_BROWSER = "1"
uv run originlab-mcp-ui
```

## Features

The server provides **65 tools** covering the OriginLab data workflow.

### Data Management (14 Tools)

| Category | Tools |
| :--- | :--- |
| Import | `import_csv` · `import_excel` · `import_data_from_text` |
| Inspect | `list_worksheets` · `get_worksheet_info` · `get_worksheet_data` · `get_cell_value` |
| Edit | `set_column_designations` · `set_column_labels` · `set_column_formula` |
| Manage | `add_worksheet` · `sort_worksheet` · `clear_worksheet` · `delete_columns` |

### Plotting (11 Tools)

| Category | Tools |
| :--- | :--- |
| Create | `create_plot` · `create_double_y_plot` |
| Modify | `add_plot_to_graph` · `remove_plot_from_graph` · `change_plot_data` · `change_plot_type` |
| Layers | `add_graph_layer` · `group_plots` |
| Inspect | `list_graphs` · `list_graph_templates` · `get_graph_info` |

### Graph Customization (25 Tools)

| Category | Tools |
| :--- | :--- |
| Axes | `set_axis_range` · `set_axis_scale` · `set_axis_step` · `set_axis_title` |
| Lines | `set_plot_line_style` · `set_plot_line_width` |
| Fonts and ticks | `set_graph_font` · `set_tick_style` |
| Colors | `set_plot_color` · `set_plot_colormap` · `set_plot_transparency` |
| Symbols | `set_plot_symbols` · `set_symbol_size` · `set_symbol_interior` |
| Group increments | `set_color_increment` · `set_symbol_increment` |
| Error bars | `set_error_bar_style` |
| Fill | `set_fill_area` |
| Legend | `set_legend` |
| Preset styling | `apply_publication_style` |
| Annotations | `set_graph_title` · `add_text_label` · `add_line_to_graph` · `remove_graph_label` |

### Analysis (3 Tools)

`linear_fit` · `nonlinear_fit` · `list_fit_functions`

> Common Origin fit functions such as Gauss, Lorentz, ExpDec1, and Boltzmann are supported. You can provide initial parameters, fix parameters, and fit with error bars.

### Export and Project Management (6 Tools)

`export_graph` · `export_all_graphs` · `export_worksheet_to_csv` · `save_project` · `open_project` · `new_project`

### System Management (4 Tools)

`get_origin_info` · `release_origin` · `reconnect_origin` · `close_origin`

### Advanced (2 Tools)

`execute_labtalk` · `get_labtalk_variable`

`execute_labtalk` is an escape hatch for operations not covered by standard tools. `get_labtalk_variable` safely reads LabTalk variable values.

## Examples

| Request | Typical tool call |
| :--- | :--- |
| Import `data.csv` into Origin | `import_csv` |
| Show worksheet columns and metadata | `get_worksheet_info` |
| Set the first column as X and the next two columns as Y | `set_column_designations` |
| Create a scatter plot | `create_plot` |
| Add another curve from the third column | `add_plot_to_graph` |
| Change the X-axis title and set the curve color to red | `set_axis_title` + `set_plot_color` |
| Apply a publication-style preset | `apply_publication_style` |
| Apply publication styling to layer 2 with line width 3 and symbol size 12 | `apply_publication_style` |
| Run a Gaussian fit | `nonlinear_fit` |
| Set the Y axis to logarithmic scale | `set_axis_scale` |
| Export a graph as PNG | `export_graph` |
| Export all project graphs as SVG | `export_all_graphs` |
| Release Origin so I can use it manually | `release_origin` |

`apply_publication_style` supports `layer_index`, axis-title font size, tick-label font size, legend font size, major tick length, minor tick count, line width, symbol size, and other common publication-figure settings.

Typical workflow:

```text
Import data -> inspect structure -> set column designations -> create plot -> customize graph -> run analysis -> export results
```

## Client Configuration

> [!NOTE]
> You do not need to start the MCP server manually. Once configured, the AI client starts the server process when needed and communicates with it over stdin/stdout.

Replace paths with your actual project path.

You can also run `uv run originlab-mcp-ui`, choose a client in the local status panel, and let it write the config automatically. Manual examples are shown below.

### Antigravity (Gemini) - Recommended

Create `.gemini/settings.json` in the project root.

**Using uv:**

```json
{
  "mcpServers": {
    "originlab": {
      "command": "uv",
      "args": ["--directory", "C:\\path\\to\\originlab-mcp", "run", "originlab-mcp"]
    }
  }
}
```

**Using pip:**

```json
{
  "mcpServers": {
    "originlab": {
      "command": "C:\\path\\to\\originlab-mcp\\.venv\\Scripts\\originlab-mcp.exe"
    }
  }
}
```

Claude Desktop

Edit `%APPDATA%\Claude\claude_desktop_config.json` using the same format as above.

Cursor

Create `.cursor/mcp.json` in the project root using the same format as above.

Trae

Create `.trae/mcp.json` in the project root using the same format as above.

Codex (OpenAI)

Create `.codex/config.json` in the project root using the same format as above.

## Testing

```powershell
# uv
uv run python -m pytest tests/ -v

# pip, after activating the virtual environment
pytest tests/ -v
```

The basic test suite does not require OriginLab to be installed.

## Project Structure

```text
originlab-mcp/
├── pyproject.toml                # Project configuration and dependencies
├── CHANGELOG.md                  # Release notes
├── scripts/
│   └── install-and-open.ps1      # One-command setup and UI launcher
├── src/originlab_mcp/
│   ├── server.py                 # MCP server entry point and dependency injection
│   ├── ui.py                     # Local status panel
│   ├── origin_manager.py         # Thread-safe Origin COM connection manager
│   ├── exceptions.py             # Custom exceptions
│   ├── types.py                  # Protocol type definitions
│   ├── tools/
│   │   ├── data.py               # Data import and worksheet management (14)
│   │   ├── plot.py               # Plot creation and graph management (11)
│   │   ├── customize.py          # Graph customization (25)
│   │   ├── analysis.py           # Linear and nonlinear fitting (3)
│   │   ├── export.py             # Export and project management (6)
│   │   ├── system.py             # System and connection management (4)
│   │   └── advanced.py           # LabTalk escape hatch (2)
│   └── utils/
│       ├── constants.py          # Enums, defaults, and fit-function metadata
│       ├── helpers.py            # Graph/sheet resolution and error handling helpers
│       └── validators.py         # Input validation and standard response builders
└── tests/
    ├── test_helpers.py           # Helper tests
    ├── test_phase3.py            # LabTalk safety and resolve-pattern tests
    ├── test_tools.py             # Tool registration and integration tests
    └── test_ui.py                # Local status panel config tests
```

## FAQ

Origin connection failed

Check that:

- OriginLab 2021 or later is installed locally
- You have a valid OriginLab license
- The current user can start Origin
- No other program is blocking the Origin COM interface

The MCP client cannot see the tools

1. Confirm the client configuration path is correct.
2. Confirm dependencies are installed with `uv sync` or `pip install -e .`.
3. Restart the MCP client.

Fit results look inaccurate

1. Check for outliers with `get_worksheet_data`.
2. Provide better initial values through `initial_params`.
3. Fix known parameters with `fixed_params`.
4. Confirm that the fit function is appropriate. Use `list_fit_functions` to inspect common options.

## License

[MIT](LICENSE) © 2025 garethbeaumo

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [garethbeaumo](https://github.com/garethbeaumo)
- **Source:** [garethbeaumo/originlab-mcp](https://github.com/garethbeaumo/originlab-mcp)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** yes
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-garethbeaumo-originlab-mcp
- Seller: https://agentstack.voostack.com/s/garethbeaumo
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.