Geekbot MCP server for AI agents

Geekbot MCP serves as a bridge connecting LLM client applications (like Claude, Cursor, Windsurf) directly to your Geekbot workspace. This allows you to interact with your standups, reports, and team members using natural language within your conversations.

Installation Options

Option 1: Installing via Smithery

To install Geekbot MCP as a remote server using Smithery:

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

The remote server will automatically update to the latest version with each release.

Option 2: Manual Installation

Prerequisites

Python 3.10 or higher
uv package manager

Step 1: Install Python 3.10+ (if needed)

macOS:

brew install [email protected]

Ubuntu/Debian:

sudo apt update
sudo apt install python3.10

Windows: Download and install from Python.org.

Step 2: Install uv

macOS/Linux:

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

Windows:

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

Step 3: Install/Upgrade Geekbot MCP

macOS/Linux/Windows:

uv tool install --upgrade geekbot-mcp

Configuration

Follow these steps to connect Geekbot MCP to your LLM client application:

Get your Geekbot API Key from your Geekbot API/Webhooks settings

Find your uv executable path:

Linux/macOS:

which uv

Windows:

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

Configure your LLM client desktop application:

Add the Geekbot MCP server to your client's configuration file:

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

Replace:

UV-PATH with the path to your uv executable
YOUR-API-KEY with your Geekbot API key

Usage Guide

Once configured, your LLM client will have access to the following tools:

Available Tools

`list_standups`

Lists all standups accessible via your API key.

Example prompt: "Can you list my Geekbot standups?"

`list_polls`

Lists all polls accessible via your API key.

Example prompt: "Show me my Geekbot polls."

`fetch_reports`

Retrieves specific standup reports with filtering options.

Example prompts:

"Fetch the reports submitted yesterday in the Retrospective."
"Show me reports from John Doe for the 'Weekly Sync' standup."
"Get all reports submitted to the Daily Standup after June 1st, 2024."

Available filters:

standup_id: Filter by specific standup ID
user_id: Filter by specific user
after/before: Date range filters (YYYY-MM-DD)

`post_report`

Posts a report to Geekbot.

Example prompt: "Post a report for the Daily Standup."

`list_members`

Lists all team members in your Geekbot workspace.

Example prompt: "Who are the members in my Geekbot workspace?"

`fetch_poll_results`

Retrieves specific poll results.

Example prompt: "What was decided about the new logo in Geekbot polls?"

Special Prompt Templates

`weekly_rollup_report`

Generates a comprehensive weekly summary of team standup responses, highlights key updates, identifies risks, and tracks upcoming launches.

Usage Tips

Review Tool Usage: Make the agent ask for your explicit approval before each tool action to maintain control over sensitive operations.
Ask for Preview: Before posting a report, request a preview to review and make changes if needed.
Limit Data Volume: When using fetch_reports, specify a reasonable date range to prevent performance issues from retrieving too much data.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

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

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect