MCP (Model Context Protocol) Server

by DrFloflo

260 downloads

Not rated

GitHub

Other

About

Omni MCP protocol, chose the right tools for you.

Details

Author: DrFloflo
Downloads: 260
Categories: Other

- Retrieve files and directory listings from GitHub repositories
- Monitor GitHub workflow runs and code search
- Run Kusto Query Language (KQL) queries on Azure Log Analytics
- Read PostgreSQL databases with read-only user support
- Search Google and YouTube, get YouTube video transcripts
- Analyze images via Azure Vision and generate responses via Azure OpenAI

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 (Model Context Protocol) 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": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

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": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

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": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

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": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

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": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

From the repository

Install dependencies via pip install -r requirements.txt, create a .env file with required tokens (GitHub PAT, Azure credentials, etc.), then run python server.py. The server starts on http://0.0.0.0:6277 by default. Docker is also supported: build with docker build -t mcp-server . and run with docker run -p 6277:6277 --env-file .env mcp-server.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "mcp (model context protocol) server": {
            "MCPo-Server": {
                "command": "python",
                "args": [
                    "server.py"
                ]
            }
        }
    }
}

McpServers

{
    "MCPo-Server": {
        "command": "python",
        "args": [
            "server.py"
        ]
    }
}

MCP (Model Context Protocol) Server

drawing

A MCP server that provides a unified interface for interacting with multiple services, currently supporting GitHub, Azure Log Analytics, Google, Azure OpenAI, Azure Vision, PostgreSQL, and more.

🔧 Features

GitHub Integration

- File/Folder Access: Retrieve files or directory listings from GitHub repositories - Workflow Monitoring: Fetch recent workflow runs and their statuses - Code Search: Search for code across repositories - Repository Structure: Get the complete file structure of a repository - Commit History: View commit history with optional file filtering - Commit Diffs: Inspect file-level changes for specific commits

Azure Integration

- Log Analytics Querying: Run Kusto Query Language (KQL) queries against Azure Log Analytics workspaces - Secure Authentication: OAuth2 client credentials flow for secure API access

Utilities

- Timestamp Generation: Get current UTC timestamp with microsecond precision - Website Content: Get the content of a website in Markdown format

Database Integration

- Database Reading: Read a database from a PostgreSQL server

> ⚠️ Use a DB user with SELECT-only privileges

Google Integration

- Google Search: Search Google for a query - YouTube Search: Search YouTube for a query - YouTube Transcript: Get the transcript of a YouTube video

Azure Vision Integration

- Image Analysis: Get the analysis of an image

LLM Integration

- Azure OpenAI: Get a response from Azure OpenAI

📦 Prerequisites

- Python 3.8+
- Docker (optional)
- Tokens & credentials:
- GitHub PAT (repo scope)
- Azure AD App: client ID, secret, tenant ID
- Azure OpenAI Key & Endpoint
- Azure Vision Key & Endpoint
- PostgreSQL credentials

Installation

1. Clone the repository:

   git clone https://github.com/DrFloflo/MCP-github.git

2. Install dependencies:

   pip install -r requirements.txt

3. Create a .env file in the project root with the following variables:

# GitHub Configuration GITHUB_TOKEN=your_github_token # Azure Configuration AZURE_CLIENT_ID=your_client_id AZURE_CLIENT_SECRET=your_client_secret AZURE_TENANT_ID=your_tenant_id # Azure OpenAI Configuration AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint AZURE_OPENAI_KEY=your_azure_openai_key AZURE_OPENAI_API_VERSION=your_azure_openai_api_version # Azure Vision Configuration VISION_ENDPOINT=your_vision_endpoint VISION_KEY=your_vision_key

# Database Configuration POSTGRES_HOST=your_postgres_host POSTGRES_PORT=your_postgres_port POSTGRES_DB=your_postgres_db POSTGRES_USER=your_postgres_user POSTGRES_PASSWORD=your_postgres_password

🔐 Token Setup

GitHub

1. Go to GitHub Personal Access Tokens
2. Generate a new token with the repo scope
3. Add this to your .env file:

Azure AD (Log Analytics)

1. Register a new app in Azure Active Directory
2. Copy the following:
- Tenant ID (Directory ID)
- Client ID (Application ID)
- Create and copy a new client secret (under Certificates & secrets)
3. Add to .env:

   AZURE_TENANT_ID=your_tenant_id

   AZURE_CLIENT_ID=your_client_id

   AZURE_CLIENT_SECRET=your_client_secret

Log Analytics Workspace

1. Go to your Log Analytics Workspace in Azure
2. Copy your Workspace ID
3. Ensure your Azure AD Application has access:
- Go to your app in Azure AD
- Navigate to API Permissions
- Click Add a permission
- Choose Microsoft Graph > Delegated permissions
- Select User.Read and confirm

Azure OpenAI

1. Go to your Azure OpenAI resource (or Foundry)
2. Copy the endpoint and key
3. Add this to .env:

   AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint

   AZURE_OPENAI_KEY=your_azure_openai_key

   AZURE_OPENAI_API_VERSION=your_azure_openai_api_version

Azure Vision

1. Go to your Azure Vision resource (or Vision)
2. Copy the endpoint and key
3. Add this to .env:

   VISION_ENDPOINT=your_vision_endpoint

   VISION_KEY=your_vision_key

PostgreSQL

1. Go to your PostgreSQL server
2. Copy the host, port, database, user, and password
3. Add this to .env:

   POSTGRES_HOST=your_postgres_host

   POSTGRES_PORT=your_postgres_port

   POSTGRES_DB=your_postgres_db

   POSTGRES_USER=your_postgres_user

   POSTGRES_PASSWORD=your_postgres_password

Usage

Running the Server

python server.py

The server will start on http://0.0.0.0:6277 by default.

Docker

Build the Docker image:

docker build -t mcp-server .

Run the container:

docker run -p 6277:6277 --env-file .env mcp-server

🧰 Available API Tools

GitHub Tools

- get_github_file_folder: Get file contents or list directories
- get_workflow_runs: Retrieve recent workflow runs
- search_codebase: Search code across repositories
- get_file_structure: Get complete repository structure
- get_commit_history: View commit history
- get_commit_diff: View file-level changes in a commit

Azure Tools

- run_log_analytics_query: Execute KQL queries against Azure Log Analytics

PostgreSQL Tools

- read_db: Query data from PostgreSQL

> ⚠️ Use a database user with read-only (SELECT) access

Google Tools

- search_google: Search Google for any query
- search_youtube: Search YouTube videos
- get_youtube_transcript: Get transcript from a YouTube video

Azure Vision Tools

- get_image_analysis: Analyze image content using Azure Vision

Azure OpenAI Tools

- get_azure_openai_response: Generate response using Azure OpenAI (LLM)

Utility Tools

- get_current_utc_timestamp: Get the current UTC timestamp
- get_website_content: Fetch and convert website HTML to Markdown

Code Tools

- execute_python_code: Execute a Python code snippet securely

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

Claude Desktop / Cursor

McpServers

MCP (Model Context Protocol) Server

🔧 Features

GitHub Integration

Azure Integration

Utilities

Database Integration

Google Integration

Azure Vision Integration

LLM Integration

📦 Prerequisites

Installation

🔐 Token Setup

GitHub

Azure AD (Log Analytics)

Log Analytics Workspace

Azure OpenAI

Azure Vision

PostgreSQL

Usage

Running the Server

Docker

🧰 Available API Tools

GitHub Tools

Azure Tools

PostgreSQL Tools

Google Tools

Azure Vision Tools

Azure OpenAI Tools

Utility Tools

Code Tools

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀