Uniquity Mcp Server

by KunihiroS

288 downloads

Not rated

GitHub

Other

About

Uniquity MCP Server is a server that makes the functions of UniquityReporter available to external tools and AI agents via MCP (Model Context Protocol).

Details

Author: KunihiroS
Downloads: 288
Categories: Other

- Generates similarity analysis reports for GitHub repositories.
- Returns reports in Markdown format via standard output.
- Supports dynamic selection of OpenAI models and log output.
- Provides a list_tools endpoint for discovering available tools.
- Relies on UniquityReporter as its core analysis engine.

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 Uniquity 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": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

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": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

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": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

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": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

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": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

From the repository

Configure the MCP host with the required environment variables (GITHUB_TOKEN, OPENAI_API_KEY, TAVILY_API_KEY) and run via npx -y uniquity-mcp@latest. Use the provided tools (analyze_repository, list_tools) to generate similarity analysis reports for GitHub repositories in Markdown format.

`analyze_repository`

Analyzes a Git repository and generates a report using Uniquity Reporter. The analysis is performed with repo=off mode, meaning no local repository copy is created or persisted.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "uniquity mcp server": {
            "uniquity-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "uniquity-mcp@latest"
                ],
                "env": {
                    "GITHUB_TOKEN": "{apikey}",
                    "OPENAI_API_KEY": "{apikey}",
                    "TAVILY_API_KEY": "{apikey}"
                }
            }
        }
    }
}

McpServers

{
    "uniquity-mcp": {
        "command": "npx",
        "args": [
            "-y",
            "uniquity-mcp@latest"
        ],
        "env": {
            "GITHUB_TOKEN": "{apikey}",
            "OPENAI_API_KEY": "{apikey}",
            "TAVILY_API_KEY": "{apikey}"
        }
    }
}

Uniquity MCP Server

Overview

Uniquity MCP Server is a server that makes the functions of UniquityReporter available to external tools and AI agents via MCP (Model Context Protocol).

> UniquityReporter: UniquityReporter

- Enables the analysis functions of UniquityReporter to be called from MCP Host or AI agents.
- Separates core logic and interface to improve maintainability and extensibility.
- Makes it available from various clients through a standardized protocol.

Release Note

- 0.1.0
- Initial version

MCP Host Settings

Required and Optional Environment Variables

- Required (Must be passed from MCP Host) - GITHUB_TOKEN: Token for GitHub API - OPENAI_API_KEY: OpenAI API key - TAVILY_API_KEY: Tavily API key - Optional (If not specified, the default values in config/config.js will be used) - openaiModel: Name of the OpenAI model to use (e.g., o3-mini, gpt-4.1-nano, etc.) - logEnabled: Enable/disable log output (on/off)

Example MCP Host Configuration

{
  "uniquity-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "uniquity-mcp@latest"
    ],
    "env": {
      "GITHUB_TOKEN": "{apikey}",
      "OPENAI_API_KEY": "{apikey}",
      "TAVILY_API_KEY": "{apikey}"
    }
  }
}

- Secrets in env settings are required. - This MCP does not support report and log file saving. - If file saving is required, save the standard output to a file on the Host side.

List of Provided Tools (MCP Server)

1. analyze_repository

- Description: Generates a similarity analysis report for the specified GitHub repository. The report is always returned in Markdown format to standard output. - Return Value: Report body in Markdown format (standard output)

| Argument | Type | Required | Description |
|-----------------|---------|----------|--------------------------------------------------|
| repositoryUrl | string | Yes | GitHub repository URL to analyze |
| openaiModel | string | No | Name of the OpenAI model to use (e.g., o3-mini, gpt-4.1-nano, etc.) |
| logEnabled | string | No | Enable/disable log output (on/off, default: off) |

2. list_tools

- Description: Returns a list of tools provided by the MCP Server and their specifications (arguments and return values). - Return Value: Array of tools available in the MCP Server (including name, description, parameterSchema, returnSchema for each tool)

| Argument | Type | Required | Description |
|----------|------|----------|-------------|
| None | | | |

---

This makes it clear to MCP Hosts and clients "what tools are available" and "how to call them."

Notes

- MCP Server supports standard output only. - openaiModel and logEnabled can be dynamically specified as tool arguments. - Optional values can be omitted, and if omitted, the default values of UniquityReporter will be used.

Version Management of Dependency Package (uniquity-reporter)

- The dependency of uniquity-reporter in package.json is specified as ^1.4.4.
- This allows minor and patch updates to be automatically followed, but major version updates (such as 2.x) will not be automatically followed.
- If you want to guarantee "always the latest," perform version updates and releases of the MCP Server itself, and recommend users to use npx uniquity-mcp@latest.

- Note on npx Cache Behavior
- npx caches the retrieved packages and dependencies.
- If you want to always use the latest version of the package and dependencies, explicitly specify "uniquity-mcp@latest" as in the MCP Host configuration example, and guide users to clear the cache (npx clear-npx-cache, etc.) for safety.

- If there are specification changes or significant updates to the dependency package, promptly version up the MCP Server and announce it in the release notes or README.

Architecture Overview

- This repository manages only the implementation of the MCP Server and depends on the uniquity-reporter npm package for core logic.
- Receives requests from MCP Host, calls UniquityReporter CLI, and returns the results.
- Uses standard input/output (stdin/stdout) based inter-process communication.
- Reports are always output to standard output and are not saved to files.

Architecture Diagram

graph LR
    subgraph MCP Host
        Client[Client Application]
    end
subgraph MCP Server

        Server[Uniquity MCP Server]

        Server -->|Command Execution| UniquityReporter[UniquityReporter CLI]

    end
subgraph External Services

        GitHub[GitHub API]

        OpenAI[OpenAI API]

        Tavily[Tavily API]

    end
Client -- MCP Protocol --> Server

    Server -- JSON Response --> Client

    UniquityReporter -- Repository Analysis --> GitHub

    UniquityReporter -- Code Analysis --> OpenAI

    UniquityReporter -- Web Search --> Tavily

Technology Stack

- Runtime: Node.js 18+
- Main Packages:
- @modelcontextprotocol/sdk: MCP protocol implementation
- uniquity-reporter: Core analysis engine
- winston: Logging
- dotenv: Environment variable management
- Development Tools:
- TypeScript
- ESLint
- Prettier
- Jest (Testing)

Project Structure

uniquity-mcp/
├── uniquity-mcp/           # Main Project
│   ├── src/
│   │   └── index.js       # Entry Point
│   └── package.json
├── .github/              # GitHub Actions Configuration
└── README.md             # This File

Development Guide

Installation

Installing Dependencies

```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

Details

Jump to

Setting up with Highlight

From the repository

analyze_repository

Claude Desktop / Cursor

McpServers

Uniquity MCP Server

Overview

Release Note

MCP Host Settings

Required and Optional Environment Variables

Example MCP Host Configuration

List of Provided Tools (MCP Server)

1. analyze_repository

2. list_tools

Notes

Version Management of Dependency Package (uniquity-reporter)

Architecture Overview

Architecture Diagram

Technology Stack

Project Structure

Development Guide

Installation

Installing Dependencies

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀

`analyze_repository`