Mcp Server To Control Openrefine
About
# OpenRefine MCP Server [](https://github.com/FiquemSabendo/openrefine_mcp/actions/workflows/test.yml) A Model Context Protocol (MCP) server that provides a typed, discoverable interface to OpenRefine's HTTP API. This allows…
Explore
This MCP server implements the following OpenRefine API endpoints:
| OpenRefine API Endpoint | MCP Implementation | Status |
|-------------------------|-------------------|---------|
| POST /command/core/create-project-from-upload | create_project(dataset_url: str, name: str \| None = None) | ✅ |
| GET /command/core/get-models | get_project_models(project_id: int) resource | ✅ |
| POST /command/core/apply-operations | apply_operations(project_id: int, operations: str) | ✅ |
| POST /command/core/export-rows | export_csv(project_id: int) | ✅ |
| POST /command/core/delete-project | delete_project(project_id: int) | ✅ |
| POST /command/core/set-project-metadata | - | ❌ |
| POST /command/core/set-project-tags | - | ❌ |
| GET /command/core/get-all-project-metadata | - | ❌ |
| POST /command/core/preview-expression | - | ❌ |
| GET /command/core/get-processes | - | ❌ |
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mcp Server To Control OpenrefineCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.13 or higher
- uv package manager
- OpenRefine instance running (default: http://localhost:3333)
uv sync
1. Create or edit your Claude Desktop configuration file:
make test
make inspector
```
- create_project(dataset_url: str, name: str | None = None) → Creates a new OpenRefine project from a dataset URL
- apply_operations(project_id: int, operations: str) → Applies operations to an OpenRefine project
- export_csv(project_id: int) → Exports CSV data from an OpenRefine project
- delete_project(project_id: int) → Deletes an OpenRefine project
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server to control openrefine": {
"openrefine": {
"command": "uv",
"args": [
"--directory",
"path/to/your/openrefine_mcp",
"run",
"openrefine_mcp/openrefine_server.py"
],
"env": {
"OPENREFINE_URL": "http://localhost:3333"
}
}
}
}
}McpServers
{
"openrefine": {
"command": "uv",
"args": [
"--directory",
"path/to/your/openrefine_mcp",
"run",
"openrefine_mcp/openrefine_server.py"
],
"env": {
"OPENREFINE_URL": "http://localhost:3333"
}
}
}OpenRefine MCP Server
A Model Context Protocol (MCP) server that provides a typed, discoverable interface to OpenRefine's HTTP API. This allows any MCP-capable client (like Claude Desktop) to orchestrate data-cleaning pipelines safely and reproducibly.
Installation
Prerequisites
- Python 3.13 or higher
- uv package manager
- OpenRefine instance running (default: http://localhost:3333)
Install the Package
# Clone the repository
git clone <repository-url>
cd openrefine_mcp
Install dependencies using uv
uv sync
Setup Claude Desktop
1. Create or edit your Claude Desktop configuration file:
# On macOS/Linux
~/.config/claude_desktop_config.json
# On Windows
%APPDATA%\claude_desktop_config.json
2. Add the OpenRefine MCP server to your configuration:
{
"mcpServers": {
"openrefine": {
"command": "uv",
"args": [
"--directory",
"path/to/your/openrefine_mcp",
"run",
"openrefine_mcp/openrefine_server.py"
],
"env": {
"OPENREFINE_URL": "http://localhost:3333"
}
}
}
}
3. Restart Claude Desktop to load the new MCP server.
Features
This MCP server implements the following OpenRefine API endpoints:
| OpenRefine API Endpoint | MCP Implementation | Status |
|-------------------------|-------------------|---------|
| POST /command/core/create-project-from-upload | create_project(dataset_url: str, name: str \| None = None) | ✅ |
| GET /command/core/get-models | get_project_models(project_id: int) resource | ✅ |
| POST /command/core/apply-operations | apply_operations(project_id: int, operations: str) | ✅ |
| POST /command/core/export-rows | export_csv(project_id: int) | ✅ |
| POST /command/core/delete-project | delete_project(project_id: int) | ✅ |
| POST /command/core/set-project-metadata | - | ❌ |
| POST /command/core/set-project-tags | - | ❌ |
| GET /command/core/get-all-project-metadata | - | ❌ |
| POST /command/core/preview-expression | - | ❌ |
| GET /command/core/get-processes | - | ❌ |
Available Tools
- create_project(dataset_url: str, name: str | None = None) → Creates a new OpenRefine project from a dataset URL
- apply_operations(project_id: int, operations: str) → Applies operations to an OpenRefine project
- export_csv(project_id: int) → Exports CSV data from an OpenRefine project
- delete_project(project_id: int) → Deletes an OpenRefine project
Available Resources
- openrefine://project/{project_id}/models → Returns structural information about the project including column definitions, record model configuration, available scripting languages, and overlay models
Development
Running Tests
make test
Running the MCP Inspector server
make inspector
License
This project is licensed under the MIT License - see the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
