xCOMET MCP Server

by shuji-bonji

554 downloads Not rated yet

GitHub Website

Other
AI

About

Translation quality evaluation using xCOMET models. Provides quality scoring (0-1), error detection with severity levels, and optimized batch processing with 25x speedup.

Explore

- Quality scoring on a 0–1 scale
- Error detection with minor, major, and critical severity levels
- Batch evaluation of up to 500 translation pairs
- GPU support for accelerated inference
- Persistent model loading for up to 177x speedup on consecutive requests
- Designed to integrate with other MCP servers like DeepL

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 xCOMET MCP Server

Command (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

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

From the repository

xCOMET requires Python with the following packages:

``bash pip install "unbabel-comet>=2.2.0" fastapi uvicorn

bash
npm install

If you prefer a local installation:`bash npm install -g xcomet-mcp-server`Then configure:`json { "mcpServers": { "xcomet": { "command": "xcomet-mcp-server" } } }



| Variable | Default | Description |

|----------|---------|-------------|

| TRANSPORT | stdio | Transport mode: stdio or http |

| PORT | 3000 | HTTP server port (when TRANSPORT=http) |

| XCOMET_MODEL | Unbabel/XCOMET-XL | xCOMET model to use |

| XCOMET_PYTHON_PATH | (auto-detect) | Python executable path (see below) |

| XCOMET_PRELOAD | false | Pre-load model at startup (v0.3.1+) |

| XCOMET_DEBUG | false | Enable verbose debug logging (v0.3.1+) |
pip install "unbabel-comet>=2.2.0" fastapi uvicorn
pip install torch --index-url https://download.pytorch.org/whl/cu118

Cause: XCOMET-XL requires ~8-10GB RAM. Solutions: 1. Use the persistent server (v0.3.0+): Model loads once and stays in memory, avoiding repeated memory spikes 2. Use a lighter model: SetXCOMET_MODEL=Unbabel/wmt22-comet-dafor lower memory usage (~3GB) 3. Reduce batch size: For large batches, process in smaller chunks (100-200 pairs) 4. Close other applications: Free up RAM before running large evaluations``bash

If you encounter issues:

1. Check the GitHub Issues
2. Enable debug logging by checking Claude Desktop's Developer Mode logs
3. Open a new issue with:
- Your OS and Python version
- The error message
- Your configuration (without sensitive data)

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "xcomet mcp server": {
            "xcomet": {
                "command": "npx",
                "args": [
                    "-y",
                    "xcomet-mcp-server"
                ]
            }
        }
    }
}

McpServers

{
    "xcomet": {
        "command": "npx",
        "args": [
            "-y",
            "xcomet-mcp-server"
        ]
    }
}

> ⚠️ This is an unofficial community project, not affiliated with Unbabel. Translation quality evaluation MCP Server powered by xCOMET (eXplainable COMET).

🎯 Overview

xCOMET MCP Server provides AI agents with the ability to evaluate machine translation quality. It integrates with the xCOMET model from Unbabel to provide: - Quality Scoring: Scores between 0-1 indicating translation quality - Error Detection: Identifies error spans with severity levels (minor/major/critical) - Batch Processing: Evaluate multiple translation pairs efficiently (optimized single model load) - GPU Support: Optional GPU acceleration for faster inference ``

mermaid
graph LR
    A[AI Agent] --> B[Node.js MCP Server]
    B --> C[Python FastAPI Server]
    C --> D[xCOMET Model<br/>Persistent in Memory]
    D --> C
    C --> B
    B --> A

    style D fill:#9f9



🔧 Prerequisites


Python Environment


xCOMET requires Python with the following packages:

bash
pip install "unbabel-comet>=2.2.0" fastapi uvicorn



Model Download


The first run will download the xCOMET model (~14GB for XL, ~42GB for XXL):

``bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Explore

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

🎯 Overview

🔧 Prerequisites

Python Environment

Model Download

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive