Dotbot
Structured, auditable AI-assisted development for teams. Zero-dependency MCP server, web dashboard, and multi-provider AI CLI support.
What is Dotbot?
Dotbot is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to structured, auditable ai-assisted development for teams. zero-dependency mcp server, web dashboard, and multi-provider ai cli support.
Structured, auditable AI-assisted development for teams. Zero-dependency MCP server, web dashboard, and multi-provider AI CLI support.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Structured, auditable AI-assisted development for teams. Zer
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx dotbotConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Dotbot
Dotbot is a zero-dependency MCP server combined with a PowerShell workflow engine and web dashboard that brings structured, auditable AI-assisted development to teams. It exposes 33 MCP tools across task management, decision tracking, session monitoring, plan creation, and steering, and integrates with Claude CLI, OpenAI Codex CLI, and Antigravity as AI providers. Engineering teams use it to run multi-step AI development pipelines with full auditability, dependency management, and per-project configuration.
Prerequisites
- PowerShell 7 or higher installed (cross-platform: Windows, macOS, or Linux)
- Git installed for cloning and worktree operations
- At least one supported AI CLI: Claude CLI, OpenAI Codex CLI, or Antigravity
- An MCP-compatible client such as Claude Desktop or Claude Code
- Optional: Playwright MCP and Context7 MCP for browser automation and documentation lookup
Install dotbot
Install dotbot using Homebrew on macOS/Linux or Scoop on Windows. Alternatively, clone the source and run the bootstrap script.
# macOS / Linux (Homebrew)
brew install andresharpe/dotbot/dotbot
# Windows (Scoop)
scoop bucket add dotbot https://github.com/andresharpe/scoop-dotbot
scoop install dotbot
# From source
git clone https://github.com/andresharpe/dotbot ~/dotbot
pwsh ~/dotbot/bootstrap.ps1Verify installation
Confirm dotbot is on your PATH and that the MCP server binary is available.
dotbot --versionInitialize a project
In your project directory, initialize a dotbot configuration. This creates the .bot/ folder with a default workflow.json and settings.
cd /path/to/your/project
dotbot initConfigure your MCP client
Add dotbot to your MCP client configuration. The server communicates over stdio and requires no additional environment variables beyond DOTBOT_HOME which is set automatically.
Define a workflow
Edit .bot/.control/workflow.json to define your multi-step AI development pipeline: tasks, dependencies, form prompts, required MCP servers, and environment constraints. Settings deep-merge across default → workflows → stacks layers.
Run a task with your AI assistant
Ask your AI assistant to create and run a dotbot task, or use the dotbot CLI directly to kick off a workflow step. The web dashboard provides real-time status and audit logs.
dotbot run --task implement-feature-xDotbot Examples
Client configuration
Claude Desktop configuration to launch dotbot as an MCP server. Adjust the command path if dotbot is not on the system PATH.
{
"mcpServers": {
"dotbot": {
"command": "dotbot",
"args": ["mcp"]
}
}
}Prompts to try
Example prompts that leverage dotbot's 33 MCP tools for structured AI-assisted development.
- "Create a new task to refactor the authentication module with a description and acceptance criteria"
- "What is the current status of all in-progress tasks in this session?"
- "Log an architectural decision: we chose PostgreSQL over MySQL because of JSONB support"
- "Show me the session statistics and token usage for today's development session"
- "Create a plan for migrating the legacy API to REST with estimated effort per step"Troubleshooting Dotbot
dotbot command not found after installation
Ensure your shell's PATH includes the Homebrew or Scoop binary directory. Run 'brew link dotbot' (macOS) or restart your terminal after Scoop install. From source, confirm bootstrap.ps1 completed without errors and that ~/dotbot/bin is on PATH.
Workflow.json settings are not being applied
Dotbot uses a deep-merge of default → workflows → stacks layers. Check that your .bot/.control/settings.json file is valid JSON and that you are running dotbot from the project root where the .bot/ directory lives.
MCP client shows 33 tools but AI CLI commands fail
Dotbot delegates AI work to an external CLI (Claude CLI, Codex CLI, or Antigravity). Verify the chosen CLI is installed and authenticated independently by running it directly in a terminal before using it through dotbot.
Frequently Asked Questions about Dotbot
What is Dotbot?
Dotbot is a Model Context Protocol (MCP) server that structured, auditable ai-assisted development for teams. zero-dependency mcp server, web dashboard, and multi-provider ai cli support. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Dotbot?
Follow the installation instructions on the Dotbot GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Dotbot?
Dotbot works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Dotbot free to use?
Yes, Dotbot is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Dotbot Alternatives — Similar Developer Tools Servers
Looking for alternatives to Dotbot? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Dotbot in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Dotbot?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.