mcpField
B
BestReads MCP Server 📚🤔

BestReads MCP Server 📚🤔

Local
github.com/dinasaur404Games & Entertainment31Updated 73w ago

About BestReads MCP Server 📚🤔

BestReads MCP Server is a remote MCP server built on Cloudflare Workers that provides personalized book recommendations. It stores user preferences in Durable Objects, generates suggestions with Workers AI, and uses GitHub OAuth for authentication.

Key features

  1. 01Remote MCP server with SSE and Streamable HTTP
  2. 02Preference storage using Durable Objects
  3. 03Book recommendations generated by Workers AI
  4. 04GitHub OAuth authentication
  5. 05Self-deployable to a Cloudflare Workers account

Use cases

  1. 01Tracking books read and favorite genres
  2. 02Excluding disliked books and authors from suggestions
  3. 03Getting book suggestions based on personal preferences

MCP support

This is an MCP server that exposes eight tools, including getProfile, addGenre, addBookRead and getBookRecommendations, to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

BestReads MCP Server 📚🤔

This is a remote MCP server, built on Cloudflare Workers, that provides personalized book recommendation.

This was built using Cloudflare's guide on deploying remote MCP servers. It uses the Agents SDK to build the MCP server, Durable Objects to persist the user's book preferences, Workers AI to generate book recommendations, and Cloudflare's OAuth Provider library to add GitHub as an authentication provider. The MCP server supports Server-Sent Events (/sse) and Streamable HTTP (/mcp) transport methods.

Get Started

To try it out, connect to https://bestreads.dinas.workers.dev/sse or https://bestreads.dinas.workers.dev/mcp, if your MCP client supports Streamable HTTP. Or, deploy it yourself using the Deploy to Cloudflare button + instructions below.

Deploy to Workers

Available Tools

  • getProfile - View your reading history and preferences
  • addGenre - Add favorite book genres
  • addFavoriteAuthor - Add authors you enjoy
  • addBookRead - Track books you've read
  • addDislikedBook - Mark books you didn't enjoy
  • addDislikedAuthor - Authors to avoid in recommendations
  • clearPreferences - Reset all preferences
  • getBookRecommendations - Get AI-powered personalized book suggestions

Deploy the MCP server

Setup
  1. Clone the repository
  git clone <your-repo-url>
  cd bestreads-mcp-server
  npm install
  1. Create a GitHub OAuth App
  • Once you create teh OAuth App, set the Authorization callback URL to https://your-worker-domain.workers.dev/callback
  • Note the ClientID and Client Secret. You will add those to your Wrangler file.
  • (Optional) Generate Cookie Encryption Key
  1. Upgrade your wrangler.toml file
[vars]
GITHUB_CLIENT_ID = "your_github_client_id"
GITHUB_CLIENT_SECRET = "your_github_client_secret"
COOKIE_ENCRYPTION_KEY = "your_32_byte_hex_key"

[[kv_namespaces]]
binding = "OAUTH_KV"
id = "your_kv_namespace_id"

[[durable_objects.bindings]]
name = "MCP_OBJECT"
class_name = "MyMCP"

[[durable_objects.bindings]]
name = "USER_BOOK_PREFERENCES"
class_name = "UserBookPreferences"
  1. Deploy to Cloudflare Workers wrangler deploy

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.