Overview
What is Runbook MCP server?
This MCP server integrates with the Runbook documentation platform to allow listing, reading, searching, creating, and updating documents, as well as running workflow processes. It is designed for users of Runbook who want to interact with their knowledge base programmatically.
How to use Runbook MCP server?
Install and configure the server using npx -y @runbook-docs/mcp-server. You must provide your Runbook subdomain base URL and API token either via environment variables (RUNBOOK_BASE_URL, RUNBOOK_API_TOKEN) or command-line arguments. The server can be used with Claude Desktop (via manual config or .mcpb extension) or Cursor.
Key features of Runbook MCP server
- List top 100 articles in a book
- Retrieve full article content by ID
- Create new articles in Markdown format
- Update existing articles by ID
- Search articles by keywords
- Run and manage workflow processes
Use cases of Runbook MCP server
- Searching a company knowledge base for relevant articles
- Automatically creating documentation from external sources
- Updating existing articles in bulk
- Running workflow processes based on article content
- Listing available books and categories to navigate content
FAQ from Runbook MCP server
What are the runtime requirements?
Node.js version 20.0.0 or higher is required.
How do I provide my Runbook credentials?
Set the RUNBOOK_BASE_URL (with your subdomain) and RUNBOOK_API_TOKEN environment variables, or pass them as command-line arguments --base-url and --api-token.
What Markdown elements are supported for article bodies?
Supported elements include headers (H2–H4), bold, italic, lists, links, code blocks, tables, blockquotes, callouts (info/warning), and Mermaid diagrams.
How do I get the full article body?
The list-articles and search-articles tools return bodies truncated to 200 characters. Use get-article with the article UID to retrieve the full content.
What ID formats are used?
Article IDs start with ar_, book IDs with bk_, category IDs with ca_,
