Playbookmcp

What is Playbookmcp

playbookMCP is a collaborative MCP server designed to facilitate the sharing of AI agent contexts among engineering teams, bridging the gap between different tools and environments.

Use cases

Use cases for playbookMCP include updating package dependencies, performing code refactoring, adding unit tests, and standardizing code formatting across different tools and team members.

How to use

To use playbookMCP, teams can convert their GitHub repository-based contexts into the MCP Server. Engineers can collaboratively edit agent contexts, version control their AI prompts, and share new capabilities instantly across their preferred coding tools.

Key features

Key features of playbookMCP include collaborative editing of agent contexts, version control for AI prompts, and immediate sharing of capabilities among team members.

Where to use

playbookMCP is applicable in software development environments where teams utilize various programming tools and require a centralized platform for context sharing and collaboration.

A collaborative MCP server for sharing playbooks between agents

📋 Motivation & Overview

Modern programming tools like Cursor, Windsurf, Augment Code, and Cline all feature powerful “agent modes” that can automatically complete complex tasks based on natural language instructions:

• Updating package dependencies and addressing CVE vulnerabilities
• Performing routine code refactoring across multiple files
• Adding unit tests for new or existing functionality
• Standardizing code formatting and fixing linting issues

However, these capabilities face a critical limitation: context sharing.

The Problem

• Each team member uses different tools (Cursor, Cline, etc.)
• Natural language “playbooks” exist only in individual environments
• No centralized way to share, version, or collaboratively improve these playbooks
• Playbook silos form as team members develop their own agent instructions

The Solution: playbookmcp

playbookmcp converts GitHub repository-based playbooks into an MCP Server that all mainstream programming tools support. This enables:

• Collaborative editing of playbooks through standard GitHub workflows
• Version control for your team’s playbooks
• Immediate sharing of new capabilities across the entire team

For example, when engineer Alice adds a new playbook for “Updating dependency versions across the monorepo,” commits it to the playbook repo, and pushes, engineer Bob immediately gains access to this capability in his preferred coding tool.

🔍 Design

Your team can continuously enrich the knowledge base by editing the playbook-repo (typically a GitHub repository), enabling AI to automatically complete various tasks.

For playbook repository structure details, see docs/playbook.md.

🚀 How to Use

Setup

Basic Configuration

To use playbookmcp with a remote playbook repository:

{
  "mcpServers": {
    "playbookmcp": {
      "command": "npx",
      "args": [
        "-y",
        "playbookmcp@latest",
        "--playbook-repo",
        "<your playbook repo>"
      ]
    }
  }
}

Local Development

For testing with a local context directory:

{
  "mcpServers": {
    "playbookmcp-local": {
      "command": "npx",
      "args": [
        "-y",
        "playbookmcp@latest",
        "--playbook-path",
        "<your playbook files path>"
      ]
    }
  }
}

PlaybookMCP Development

For developing PlaybookMCP itself:

{
  "mcpServers": {
    "playbookmcp-dev": {
      "command": "node",
      "args": [
        "build/index.js",
        "--playbook-path",
        "<your playbook files path>"
      ]
    }
  }
}

You can also use inspector to inspect the MCP resources:

npx @modelcontextprotocol/inspector node build/index.js --playbook-repo <your playbook repo>

Chat with Your Code-Agent

Below is an example configuration in Cursor:

{
  "mcpServers": {
    "playbookmcp": {
      "command": "npx",
      "args": [
        "-y",
        "playbookmcp@latest",
        "--playbook-repo",
        "[email protected]:xuezhaojun/PlaybookMCP-demo.git"
      ]
    }
  }
}

The first command must be pb_start to initiate interaction:

pb_start Say Hi to playbookmcp.

Or more specific:

use MCP tool pb_start Say hi to playbookmcp.

Your code-agent will then add a comment on this issue.