GibsonAI MCP Server

What does “GibsonAI” MCP Server do?

The GibsonAI MCP (Model Context Protocol) Server serves as a bridge between AI assistants and your GibsonAI projects and databases. It allows MCP-compatible clients—such as Cursor, Windsurf, Claude Desktop, and others—to perform a wide range of project and database management tasks using natural language instructions. By leveraging GibsonAI MCP Server, users can create new projects, design and modify database schemas, execute SQL queries, manage deployments, seed tables with mock data, and more, all directly from within their favorite development environments. This integration streamlines the development workflow, enabling seamless interaction with databases and project resources through conversational AI.

List of Prompts

• “Create a blogging platform schema with users, posts, and comments.”
  • Generates a database schema for a blogging platform.
• “Add a foreign key from bookings to payments.”
  • Modifies the schema to add relationships.
• “Generate mock data for the booking destination table.”
  • Creates mock data for database tables.
• “Fetch connection string for my blogging database.”
  • Retrieves database connection details.
• “Explain how the tables are related in this project.”
  • Summarizes relationships between tables.

List of Resources

• GibsonAI Projects
  • Access and manage your GibsonAI project files and metadata.
• Database Schemas
  • View and modify schemas for databases within a project.
• Tables and Relationships
  • Explore tables, their structures, and inter-table relationships.
• Project Deployments
  • Manage and view deployment environments for projects.

List of Tools

• Project Creation Tool
  • Create new GibsonAI projects from natural language commands.
• Schema Designer Tool
  • Design, view, and modify database schemas interactively.
• SQL Query Tool
  • Run SQL queries directly against your configured databases.
• Data Seeder Tool
  • Seed tables with automatically generated mock data.
• Deployment Tool
  • Deploy projects to development or production environments.

Use Cases of this MCP Server

• Database Management
  Effortlessly create, modify, and visualize complex database schemas using natural language, accelerating development and reducing manual errors.
• Codebase Exploration
  Gain insights into project structure, table relationships, and schema diagrams to quickly understand and navigate large projects.
• Schema Migrations
  Apply schema changes and trigger automatic migrations, ensuring that database structure evolves smoothly with application needs.
• Mock Data Generation
  Populate tables with mock data for development and testing, speeding up prototyping and validation processes.
• Automated Deployment
  Deploy projects to various environments directly from the IDE, simplifying the release process and reducing context switches.

How to set it up

Windsurf

1. Go to Windsurf → Settings → Windsurf Settings → Cascade
2. Click Add server in the Model Context Protocol (MCP) Servers section.
3. Click Add custom server in the modal dialog.
4. Update the configuration to include:

   {
     "mcpServers": {
       "gibson": {
         "command": "uvx",
         "args": ["--from", "gibson-cli@latest", "gibson", "mcp", "run"]
       }
     }
   }
   

5. Open the Cascade chat and refresh the MCP servers if necessary.

Note: Secure API keys and sensitive environment variables via your system’s environment configuration.

Claude

1. Go to Claude → Settings → Developer and click Edit Config.
2. Open the claude_desktop_config.json file.
3. Add the GibsonAI MCP server configuration:

   {
     "mcpServers": {
       "gibson": {
         "command": "uvx",
         "args": ["--from", "gibson-cli@latest", "gibson", "mcp", "run"]
       }
     }
   }
   

4. Save and restart Claude Desktop if needed.

Note: Secure API keys via environment variables where appropriate.

Cursor

1. Click the “Add to Cursor” button (if available) or go to Cursor → Settings → Cursor Settings → MCP Tools.
2. Click New MCP Server.
3. Update the configuration as follows:

   {
     "mcpServers": {
       "gibson": {
         "command": "uvx",
         "args": ["--from", "gibson-cli@latest", "gibson", "mcp", "run"]
       }
     }
   }
   

4. Save and restart Cursor as needed.

Note: Secure API keys via environment variables.

Cline

1. Follow instructions for your VS Code extension workflow.
2. Add the following to your .vscode/mcp.json file:

   {
     "inputs": [],
     "servers": {
       "gibson": {
         "type": "stdio",
         "command": "uvx",
         "args": ["--from", "gibson-cli@latest", "gibson", "mcp", "run"]
       }
     }
   }
   

3. Save the configuration and reload the extension.

Note: Secure API keys using environment variables.

Example of securing API keys in JSON configurations:

{
  "mcpServers": {
    "gibson": {
      "command": "uvx",
      "args": ["--from", "gibson-cli@latest", "gibson", "mcp", "run"],
      "env": {
        "GIBSON_API_KEY": "${GIBSON_API_KEY}"
      },
      "inputs": []
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "gibson": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “gibson” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the tables above, GibsonAI MCP Server scores highly for documentation and feature clarity, but lacks explicit mention of advanced MCP features like sampling and roots. It provides practical setup guidance and a reasonable set of tools/resources for most development workflows.

Our opinion

The GibsonAI MCP Server is well-documented and easy to set up for several popular AI development platforms. While it covers essential project and database management use cases, it does not mention support for advanced MCP features such as sampling or roots, which may limit some agentic or boundary-aware workflows. Overall, it is a solid and practical MCP server for developers working with GibsonAI projects.

MCP Score