MCP Playbook Server

Name: MCP Playbook Server
Author: dwarvesf

@dwarvesf

About MCP Playbook Server

A Model Context Protocol (MCP) server for managing project documentation and saving conversation logs within a user-specified target project directory.

#mcp-playbook #project-management #documentation

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-playbook": {
      "command": "npx",
      "args": [
        "-y",
        "@dwarvesf/mcp-playbook@latest"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token_here"
      }
    }
  }
}

Tools

Provides an instruction to the LLM about the purpose of the mcp-playbook server, which is to facilitate local project documentation and enable partial replication of documentation and chat logs for an AI-powered playbook.

Creates or overwrites a new specification file (e.g., PRD, RFC, architectural planning) in the docs/specs/ directory of the target project. Specification files will be named following a `spec-name.md` convention with sequence numbering.

Creates or overwrites a new Architectural Decision Record (ADR) file in the docs/adr/ directory of the target project. ADR files will be named following an `adr-name.md` convention with sequence numbering.

Creates a new, detailed, and user-facing changelog entry file in the docs/changelog/ directory of the target project. Each changelog entry will be a separate file named following a `changelog-entry.md` convention with sequence numbering.

Creates or updates the central `docs/runbook.md` file within the target project. The LLM is responsible for analyzing existing project documents (ADRs, specs, etc.) and the current `docs/runbook.md` (if it exists), then synthesizing this information into a comprehensive runbook. The tool saves this LLM-generated content, overwriting the previous `docs/runbook.md`.

Captures the current conversation history, saves it as a markdown file in the .chat/ directory of the target project, and uploads it to the dwarvesf/prompt-log GitHub repository. Requires a user ID for organization.

Fuzzy search for keywords in the `dwarvesf/runbook` GitHub repository. If keyword has spaces, searches exact phrase OR individual words. Returns top 5 matches with full content & total count.

Fuzzy search for keywords in the `dwarvesf/prompt-db` GitHub repository (excluding the `.synced_prompts/` folder).

Creates or updates a Pull Request in the dwarvesf/runbook repository with a new runbook entry.

Syncs an LLM prompt to the dwarvesf/prompt-db GitHub repository.

Use the tool to think about something. It will not obtain new information or make any changes to the repository, but just log the thought. Use it when complex reasoning or brainstorming is needed.

Overview

What is MCP Playbook Server?

A Model Context Protocol (MCP) server that helps LLMs manage project documentation and save conversation logs within a user‑specified target project directory. It is a self-contained Node.js/TypeScript application designed for teams using AI‑assisted development workflows.

How to use MCP Playbook Server?

Configure the server in your MCP client (e.g., Claude Desktop) by adding an entry with npx -y @dwarvesf/mcp-playbook@latest and your GitHub Personal Access Token. Include the rule “ALWAYS run the init_playbook tool before starting” in your cursor, cline, or windsurf rules.