Geekbot MCP

How to Install and Use Geekbot MCP

Geekbot MCP (Model Context Protocol) is a useful server that connects your LLM client apps—like Claude, Cursor, or Windsurf—directly to your Geekbot workspace. This makes it easy to manage standups, polls, reports, and team members right from your conversations.

Installing Geekbot MCP

Before you start using Geekbot MCP, you need to install it. There are two ways to install it: via Smithery or manually. Let's look at both methods.

Installing via Smithery

If you want a simple one-line installation that keeps your server up-to-date, Smithery is the way to go. Here’s how to install Geekbot MCP as a remote server using Smithery:

npx -y @smithery/cli install @geekbot-com/geekbot-mcp --client claude

This command installs the Geekbot MCP server and automatically updates it to the latest version whenever a new release comes out.

Manual Installation

If you prefer manual setup or don’t want to use Smithery, follow these steps. First, make sure you have Python 3.10 or higher and the uv tool installed.

Step 1: Install Python 3.10+

• For macOS, run in the Terminal:

brew install [email protected]

• For Ubuntu/Debian, run:

sudo apt update
sudo apt install python3.10

• For Windows, download and install Python from python.org.

Step 2: Install uv command-line tool

• On macOS/Linux, use this Terminal command:

curl -LsSf https://astral.sh/uv/install.sh | sh

• On Windows, open PowerShell and run:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Step 3: Install or upgrade Geekbot MCP

Finally, install Geekbot MCP using the uv tool by running this on macOS/Linux Terminal or Windows PowerShell:

uv tool install --upgrade geekbot-mcp

Now Geekbot MCP is installed and ready to be configured!

Configuring Geekbot MCP

After installation, you need to link Geekbot MCP with your LLM client app.

Step 1: Get your Geekbot API Key

Go to your Geekbot dashboard at Geekbot API/Webhooks settings and copy your API key. This key allows Geekbot MCP to access your data.

Step 2: Find the uv executable path

• On Linux/macOS, in your terminal:

which uv

• On Windows PowerShell:

(Get-Command uv | Select-Object -ExpandProperty Path) -replace '\\', '\'

Step 3: Edit your LLM client config

Open your LLM client’s configuration file (like Claude Desktop, Cursor, or Windsurf) and add the Geekbot MCP server setup like this:

{
  "mcpServers": {
    "geekbot-mcp": {
      "command": "UV-PATH",
      "args": [
        "tool",
        "run",
        "geekbot-mcp"
      ],
      "env": {
        "GB_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Remember to replace UV-PATH with your actual uv path from Step 2, and YOUR-API-KEY with your API key from Step 1.

Using Geekbot MCP

Once Geekbot MCP is connected to your LLM client, you can easily interact with your Geekbot workspace. You can list standups, fetch reports, post new reports, view team members, and more—all through natural language prompts.

For example, to list your standups, just ask:

"Hey, can you list my Geekbot standups?"

Geekbot MCP supports many helpful commands, making managing your standups and polls seamless.

---

By following these easy steps, you can install, set up, and start using Geekbot MCP quickly. This bridge between your LLM apps and Geekbot workspace unlocks new ways to work together smoothly!