Runbook MCP server

@qloba

About Runbook MCP server

No overview available yet

Config

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

{
  "mcpServers": {
    "runbook": {
      "command": "npx",
      "args": [
        "-y",
        "@runbook-docs/mcp-server"
      ],
      "env": {
        "RUNBOOK_BASE_URL": "https://<YOUR_SUBDOMAIN>.runbook.jp",
        "RUNBOOK_API_TOKEN": "your-api-token"
      }
    }
  }
}

Tools

Search for articles using keywords from Runbook. The result does not include full article bodies as they are truncated to 200 characters. You will need to retrieve the full content by calling `runbook-get-article`

Retrieve the article by its ID or URL from the database.

List top 100 articles in a specified book with ID. The result does not include full article bodies as they are truncated to 200 characters. You will need to retrieve the full content by calling `runbook-get-article`.

Create a new article in a specified book with ID. The article body is in Markdown format. The article will be created in the root folder of the book. You can specify categories for the article by their IDs, which always start with 'ca_' You can retrieve a list of books with `runbook-list-books` and categories with `runbook-list-categories`. Markdown format supports: - Headers: ## H2, ### H3, #### H4. Don't use # H1 as it is reserved for the article title. - Bold: **bold text** - Italic: _italic text_ - Lists: - item or 1. numbered item - Links: [text](url) - Code blocks: ```\ncode\n``` - Tables: | col1 | col2 |\n| --- | --- |\n| data | data | - Blockquotes: > quoted text - Callouts: :::callout info\ntext\n::: or :::callout warning\ntext\n::: - Diagrams: ```mermaid\ngraph TD;\n```

Update an existing article by its ID. The article body is in Markdown format. You can specify categories for the article by their IDs, which always start with 'ca_'. Markdown format supports: - Headers: ## H2, ### H3, #### H4. Don't use # H1 as it is reserved for the article title. - Bold: **bold text** - Italic: _italic text_ - Lists: - item or 1. numbered item - Links: [text](url) - Code blocks: ```\ncode\n``` - Tables: | col1 | col2 |\n| --- | --- |\n| data | data | - Blockquotes: > quoted text - Callouts: :::callout info\ntext\n::: or :::callout warning\ntext\n::: - Diagrams: ```mermaid\ngraph TD;\n```

List top 100 books in the organization

List top 100 categories in a specified book with ID

Retrieve a folder in a book with its ancestors and children (subfolders and articles). If `folderUid` is not provided, the root folder of the book will be retrieved. The articles in the result include only a name and UID. To get the full article body, call `runbook-get-article`.

Get a list of processes assigned to the current user

Get current process information by book UID

This tool is used to start a new process or continue an existing one. If the run state UID is not provided, a new process will be created. Before executing run-process, you must call get-process and follow its instructions.

Get a presigned URL to upload an attachment file for a running process. This tool does NOT upload the file itself. It returns an `upload_url` that you must use to upload the file contents via HTTP PUT (e.g., `curl -X PUT --upload-file <path> "<upload_url>"` or `fetch(upload_url, { method: 'PUT', body: <content> })`). Set the `Content-Type` header to match the `content_type` if provided. After uploading, pass the returned `uid` to run-process propertyValues as an array of UIDs. # Example: ## article body :::input file { uid="1:mgkxg1t4jq1sehs47s40xs70wr" required=true readOnly=false } Attachment files <input type="file" name="1:mgkxg1t4jq1sehs47s40xs70wr" /> ::: ## property values { "1:mgkxg1t4jq1sehs47s40xs70wr" : ["<FILE_UID>"] }

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_,

Frequently asked questions