Publish, update, browse, and delete Booklet Markdown pages through MCP tools, resources, and document templates.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag โ we're steadily working through the catalog.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Booklet.
The booklet MCP server gives MCP-compatible assistants access to Booklet's page-management API. It is intended for workflows where an assistant needs to publish Markdown, revise an existing page, inspect page content, enumerate pages, or remove a page. The server works with Booklet's authenticated API and uses the same API keys as the REST interface.
Published pages are also available as MCP resources. An assistant can browse or read a page through a booklet://pages/:id resource URI, in addition to calling page-management tools. The repository also defines five prompts for common document types: incident reports, Architecture Decision Records, release notes, RFCs, and runbooks.
The hosted service is available at https://booklet-mcp.ashwinsathian.com/mcp. Clients send the Booklet API key in an Authorization: Bearer <bklt_...> header. The MCP process then exposes Booklet operations through the protocol while Booklet handles page storage and API authentication.
The available tools are publish_page, update_page, get_page, list_pages, and delete_page. These correspond to creating a page, changing one, retrieving one, listing pages, and deleting one. Page content is Markdown, matching Booklet's normal publishing model. This makes the booklet MCP server suitable for assistants that generate documentation or maintain pages after reviewing source material.
Point an MCP-compatible client at the hosted endpoint and provide a Booklet API key as the bearer credential. The project documentation provides copy-ready setup examples for Claude Desktop, Claude.ai, Cursor, Windsurf, VS Code, and Zed. API keys are the same credentials used by Booklet's REST API.
For local development, enter the mcp-server directory and run npm run dev. The README describes the MCP implementation as a plain Node process run under PM2 alongside the main application. The hosted service is not described as a Cloudflare Worker; that earlier deployment approach was replaced.
publish_page.update_page.get_page.list_pages.delete_page.booklet://pages/:id resources.The MCP layer focuses on page operations. Booklet itself also offers a CLI, REST API, version history, analytics, collections, password protection, custom slugs, and other product features, but those are not listed as separate MCP tools in the provided material.
The server requires a valid Booklet API key and an MCP client that can connect to the supplied endpoint. The provided documentation does not list environment variable names for configuring the hosted MCP connection. It also does not specify additional MCP tools for API-key administration, collections, analytics, version history, or webhooks.
The local command starts the MCP server for development, but the excerpt does not provide a separate local endpoint, a complete local configuration file, or detailed request schemas for each tool. Consult Booklet's MCP setup page and API documentation for client-specific configuration and payload details.
Factual signals from GitHub, npm, and our automated checks โ not a rating.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/booklet)<a href="https://allmcps.com/mcp/booklet"><img src="https://allmcps.com/api/badge/booklet?style=directory" alt="Booklet on AllMCPs" /></a>