- Explore MCP Servers
- mcp-gcp
Mcp Gcp
What is Mcp Gcp
MCP-GCP is a powerful Machine Control Protocol server that integrates with Google Cloud Platform (GCP) to facilitate the management of cloud resources through natural language interactions.
Use cases
Use cases include automating cloud resource management tasks, simplifying the management of GCP instances and disks, and providing a conversational interface for developers and system administrators.
How to use
To use MCP-GCP, you can interact with it through conversational interfaces like Claude Desktop and Cursor IDE. Users can create, modify, and manage GCP resources by issuing natural language commands.
Key features
Key features include instance management (creating, modifying, and operating instances), disk management (adding and modifying disks), and network management (configuring network interfaces and IP addresses).
Where to use
MCP-GCP can be used in various fields including cloud computing, DevOps, and IT management, where efficient resource management and automation are required.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp Gcp
MCP-GCP is a powerful Machine Control Protocol server that integrates with Google Cloud Platform (GCP) to facilitate the management of cloud resources through natural language interactions.
Use cases
Use cases include automating cloud resource management tasks, simplifying the management of GCP instances and disks, and providing a conversational interface for developers and system administrators.
How to use
To use MCP-GCP, you can interact with it through conversational interfaces like Claude Desktop and Cursor IDE. Users can create, modify, and manage GCP resources by issuing natural language commands.
Key features
Key features include instance management (creating, modifying, and operating instances), disk management (adding and modifying disks), and network management (configuring network interfaces and IP addresses).
Where to use
MCP-GCP can be used in various fields including cloud computing, DevOps, and IT management, where efficient resource management and automation are required.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
MCP-GCP Integration Server
A powerful MCP (Machine Control Protocol) server that integrates with Google Cloud Platform (GCP) to provide seamless management of cloud resources through natural language interactions.
Overview
This project implements an MCP server that bridges the gap between natural language processing and GCP resource management. It allows users to control and manage GCP resources through conversational interfaces like Claude Desktop and Cursor IDE.
Features
Instance Management
-
Create Instances: Create new GCP instances with custom configurations
- Machine type selection
- Network interface configuration
- Disk configuration
- Labels and metadata
- Source image selection
-
Modify Instances: Comprehensive instance modification capabilities
- Machine type changes
- Network interface updates
- Disk modifications
- Label and metadata updates
- Stop-edit-start workflow for major changes
-
Instance Operations
- Start instances
- Stop instances
- Restart instances
- Delete instances
- List instances
- Get instance details
Disk Management
- Disk Operations
- Add new disks to instances
- Modify existing disks (size, type)
- Attach existing disks
- Detach disks
- Configure disk properties (auto-delete, mode)
Network Management
- Network Interface Configuration
- Configure network interfaces
- Set up access configurations
- Manage IP addresses
Integration Guide
Transport Types
The MCP server supports two transport types for communication:
-
stdio (Standard Input/Output)
- Direct communication through standard input/output streams
- Suitable for local development and testing
- Lower latency
- No network configuration required
-
SSE (Server-Sent Events)
- HTTP-based communication
- Suitable for production environments
- Supports multiple clients
- Better for web-based integrations
Claude Desktop Integration
Using stdio Transport
- Install Claude Desktop from Anthropic’s website
- Configure Claude Desktop to use the MCP server with stdio:
{ "mcpServers": { "mcp-gcp": { "command": "uv", "args": [ "run main.py", "--transport", "stdio" ] } } } - Start the MCP server:
uv run main.py --transport stdio
Using SSE Transport
- Install Claude Desktop
- Configure Claude Desktop to use the MCP server with SSE:
{ "mcpServers": { "mcp-gcp": { "url": "http://localhost:8000/mcp", "transport": "sse" } } } - Start the MCP server:
uv run main.py --transport sse --port 8000
Cursor IDE Integration
Using stdio Transport
- Install Cursor IDE from Cursor’s website
- Configure Cursor to use the MCP server with stdio:
{ "mcp": { "servers": { "mcp-gcp": { "command": "uv", "args": [ "run main.py", "--transport", "stdio" ] } } } } - Start the MCP server:
python src/server/mcpserver.py --transport stdio
Using SSE Transport
- Install Cursor IDE
- Configure Cursor to use the MCP server with SSE:
{ "mcp": { "servers": { "mcp-gcp": { "url": "http://localhost:8000/mcp", "transport": "sse" } } } } - Start the MCP server:
python src/server/mcpserver.py --transport sse --port 8000
Architecture
graph TD A[User Interface] -->|Natural Language| B[Claude Desktop/Cursor] B -->|MCP Protocol| C[MCP Server] C -->|API Calls| D[GCP Service] D -->|Resource Management| E[GCP Resources] subgraph "MCP Server Components" C --> F[Intent Parser] F --> G[GCP Tools] G --> H[GCP Service] end subgraph "GCP Resources" E --> I[Compute Instances] E --> J[Disks] E --> K[Networks] end
System Flow
sequenceDiagram participant User participant Claude/Cursor participant MCP Server participant GCP API User->>Claude/Cursor: Natural Language Request Claude/Cursor->>MCP Server: MCP Protocol Request MCP Server->>MCP Server: Parse Intent MCP Server->>MCP Server: Select Appropriate Tool MCP Server->>GCP API: API Call GCP API-->>MCP Server: Response MCP Server-->>Claude/Cursor: Formatted Response Claude/Cursor-->>User: Natural Language Response
Getting Started
-
Clone the repository:
git clone https://github.com/yourusername/mcp-gcp.git cd mcp-gcp -
Install dependencies:
uv install -r requirements.txt -
Configure GCP credentials:
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/credentials.json export GCP_PROJECT_ID=your-project-id -
Start the MCP server:
uv run main.py -
Configure your preferred interface (Claude Desktop or Cursor) to connect to the MCP server.
Example Usage
Instance Management
# Create a new instance
"Create a new instance named 'web-server' with 2 vCPUs and 4GB RAM"
# Modify an instance
"Change the machine type of 'web-server' to n2-standard-2"
# Manage disks
"Add a 100GB SSD disk to 'web-server'"
"Attach the existing disk 'data-disk-1' to 'web-server'"
# Instance operations
"Start the instance 'web-server'"
"Stop the instance 'web-server'"
"Delete the instance 'web-server'"
Resource Monitoring
# List resources
"Show me all instances in asia-southeast1-b"
"List all disks attached to 'web-server'"
# Get details
"Show me the details of instance 'web-server'"
"What's the status of disk 'data-disk-1'?"
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










