ThinkGeo MCP Server¶

The ThinkGeo MCP Server allows AI assistants and development tools to access ThinkGeo documentation and resources directly through the Model Context Protocol (MCP).

By connecting an MCP‑compatible AI client to the ThinkGeo Documentation MCP endpoint, developers can ask natural‑language questions about ThinkGeo APIs, libraries, and mapping workflows and receive accurate answers based on the latest ThinkGeo documentation, community posts and samples.

MCP Server URL: https://ai.thinkgeo.com/mcp

What Is MCP?¶

he Model Context Protocol (MCP) is an open standard that allows AI applications to connect to external tools, services, and data sources in real time. Instead of relying solely on their training data, AI models can query MCP servers to retrieve up‑to‑date information or execute specialized tools.

What's Included¶

The server indexes over 12,700 documents across the full ThinkGeo product ecosystem:

What You Can Do With It¶

Once connected, you can ask your AI assistant natural language questions about ThinkGeo APIs and expect answers grounded in real documentation. Some examples:

• "Show me how to add a ShapeFileFeatureLayer to a WPF map."
• "How do I style features using ClassBreakStyle in WinForms?"
• "Generate a Blazor page that displays a ThinkGeo map with a background tile overlay."
• "What WFS endpoints does ThinkGeo GIS Server support?"
• "How do I add routing to a .NET MAUI app using ThinkGeo Cloud?"

Or, use Claude Code or Codex directly in your ThinkGeo maps project and ask it for help generating new features and fixing bugs.

Available MCP Tools¶

The server exposes the following tools to MCP-compatible AI clients:

Setting Up in Desktop AI Assistants¶

Claude Desktop¶

1. Open your Claude Desktop configuration file:
2. macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

3. Windows: %APPDATA%\Claude\claude_desktop_config.json

4. Add the ThinkGeo MCP server entry under mcpServers:

{
  "mcpServers": {
    "thinkgeo-docs": {
      "type": "url",
      "url": "https://ai.thinkgeo.com/mcp"
    }
  }
}

1. Save the file and restart Claude Desktop. The ThinkGeo documentation tools will be available automatically in all conversations.

ChatGPT (Plus, Team, or Enterprise)¶

1. Go to Settings → Connectors (or Tools depending on your plan).
2. Select Add MCP Server.
3. Enter the server URL: https://ai.thinkgeo.com/mcp
4. Give it a name such as ThinkGeo Docs and save.

Once connected, you can ask ThinkGeo-related questions and ChatGPT will query the documentation server to ground its answers.

Grok (xAI)¶

1. Open Grok's settings and navigate to Integrations or MCP Connections.
2. Add a new MCP server with the URL: https://ai.thinkgeo.com/mcp
3. Save and restart your session.

Gemini (Google)¶

For Gemini CLI or Gemini-based tools that support MCP, add the server configuration per the tool's documentation, using:

https://ai.thinkgeo.com/mcp

Refer to Google's current MCP integration documentation for the exact configuration file location and format, as this may vary by product and version.

Setting Up in Developer Tools and IDEs¶

Visual Studio Code (GitHub Copilot Agent Mode)¶

1. Open your VS Code workspace or user settings (Ctrl+Shift+P → Open User Settings JSON).
2. Add the following to your MCP server configuration:

{
  "mcp": {
    "servers": {
      "thinkgeo-docs": {
        "type": "http",
        "url": "https://ai.thinkgeo.com/mcp"
      }
    }
  }
}

1. Switch GitHub Copilot Chat to Agent mode and reference the server in your prompt, for example:

"Using the ThinkGeo docs, show me how to add a VectorTileLayer in WPF."

Visual Studio 2022¶

1. Ensure you have the GitHub Copilot extension installed and updated to the latest version.
2. Open Tools → Options → GitHub Copilot → MCP Servers.
3. Add a new entry with URL https://ai.thinkgeo.com/mcp and name it ThinkGeo Docs.
4. In Copilot Chat, switch to Agent mode and tag the MCP server in your queries.

Cursor IDE¶

1. Open Cursor's settings and navigate to MCP in the left panel.
2. Click Add New MCP Server.
3. Set the type to Streamable HTTP and enter: https://ai.thinkgeo.com/mcp
4. Name it ThinkGeo Docs and click Save.

Once configured, Cursor's AI will automatically consult the ThinkGeo documentation when answering ThinkGeo-related questions.

JetBrains Rider / IntelliJ IDEA¶

1. Open Settings → Tools → AI Assistant → MCP Servers.
2. Click the + icon to add a new server.
3. Enter https://ai.thinkgeo.com/mcp as the URL and save.

The JetBrains AI Assistant will now be able to query ThinkGeo documentation directly from within Rider or any other JetBrains IDE.

Claude Code (CLI)¶

If you use Claude Code from the command line, add the MCP server to your project or global configuration:

claude mcp add thinkgeo-docs --url https://ai.thinkgeo.com/mcp

Or manually edit your claude_code_config.json:

{
  "mcpServers": {
    "thinkgeo-docs": {
      "type": "url",
      "url": "https://ai.thinkgeo.com/mcp"
    }
  }
}

Gemini CLI¶

For the Gemini CLI tool, add the ThinkGeo MCP server to your .gemini/settings.json:

{
  "mcpServers": {
    "thinkgeo-docs": {
      "httpUrl": "https://ai.thinkgeo.com/mcp"
    }
  }
}

Tips for Getting the Best Results¶

• Be specific about the product. Mention the platform you're targeting — WPF, WinForms, Blazor, MAUI, or GIS Server — so the AI can search the right namespace.
• Ask for code examples. The server includes full "How Do I" solution files, so asking for working code samples will often yield complete, runnable snippets.
• Combine with your project context. Paste in a relevant class or method from your project alongside your ThinkGeo question for the most accurate AI-generated code.
• Always review generated code. AI output can vary depending on your prompt and model. Verify generated code for correctness, architectural fit, and security before using it in production.

Need Help?¶

• Documentation: docs.thinkgeo.com
• Community Forum: community.thinkgeo.com
• Support Helpdesk: helpdesk.thinkgeo.com