Skip to main content
Glama

hardcover-oauth-mcp

A remote Model Context Protocol (MCP) server for Hardcover, the book tracking site. It lets Claude and other MCP clients read and manage your library, reading progress, reviews, journal, lists, goals, and more.

  • Works in web and mobile clients. The public instance is a hosted remote server, so Claude on the web and on phones, ChatGPT, and other remote clients can connect to it. Other Hardcover MCP servers run on your own computer, where only desktop clients can reach them.

  • Sign in with Hardcover (OAuth). No pasting unsafe API keys. Each person connects their own account through Hardcover's OAuth and picks which permissions to grant.

  • 53 read/write tools. 47 custom task-oriented tools cover the library, progress, reviews, journal, lists, goals, follows, notifications, and vibes. Six raw GraphQL and schema-discovery tools reach anything else in the Hardcover API.

Connect to the public instance at https://hardcover.benjuntilla.com/mcp (quick start) or deploy your own.

Example workflows

Track a book

  1. "I'm on page 212 of Piranesi." The book moves to Currently Reading and the page goes on its reading session.

  2. "Finished it today, 4.5 stars." The book moves to Read, finished today, with a 4.5-star rating.

Plan what's next

  1. "Add Kindred and The Dispossessed to my want-to-read."

  2. "Make a ranked list called Summer with both, Kindred first."

  3. "Move The Dispossessed to the top."

Set a reading goal

  1. "Set a goal of 30 books this year."

  2. "How am I doing on my goal?"

Keep a journal

  1. "Save this quote from Piranesi: 'The Beauty of the House is immeasurable; its Kindness infinite.'"

  2. "Show my notes on Piranesi."

Pick an edition

  1. "Which audiobook editions of Dune are there, and how long are they?"

  2. "Switch my copy to the shortest one."

Ask anything else

  1. "Which of the books I read last year had the most pages?" With no tool for that, the client looks up the API with hardcover_find_operations and runs a read-only hardcover_query.

  2. "Answer the prompt 'What book made you cry uncontrollably?' with Kindred." The client finds the prompt with hardcover_search, looks up the mutation with hardcover_find_operations, and runs hardcover_mutate.

Related MCP server: hardcover-mcp

Quick start

Anyone with a Hardcover account can use the public instance. Add this URL to your MCP client as a remote server:

https://hardcover.benjuntilla.com/mcp
  • Claude (web, desktop, mobile): Settings → Connectors → Add custom connector, then paste the URL.

  • Claude Code: claude mcp add --transport http hardcover https://hardcover.benjuntilla.com/mcp, then run /mcp to sign in.

  • ChatGPT (web, desktop, mobile): on chatgpt.com, open Plugins, select + → Add custom MCP server, paste the URL, keep OAuth as the authentication, and create it. Type @ in a chat to use it.

  • Cursor and others: add a remote (Streamable HTTP) server with that URL. The client discovers OAuth by itself.

  • MCP Inspector: bunx @modelcontextprotocol/inspector, choose Streamable HTTP, and enter the URL.

Your client opens a consent page where you pick permissions, then Hardcover asks you to sign in. Revoke access any time from Hardcover's Authorized apps page. See the privacy notice and terms, or deploy your own.

Report an issue

Something not working? Open an issue on GitHub, or email ben@benjuntilla.com. For security problems, follow the security policy instead.

How it works

It runs on the Cloudflare Developer Platform (Workers, Durable Objects, and KV), chosen for its convenient developer experience and cost efficiency. A Durable Object per connection holds the tokens and serves MCP; KV holds OAuth state. Alchemy deploys it in one command, and alchemy dev runs the same code locally. It's built with Effect 4 (including Effect's own MCP server), TypeScript 7, Bun, mise, and Astro.

┌──────────────┐  MCP + OAuth 2.1   ┌──────────────────────────────┐
│ MCP client   │ ─────────────────▶ │ Worker                       │
│ (Claude, …)  │ ◀───────────────── │  OAuthProvider, consent page │
└──────────────┘  MCP access token  │  auth + rate limits on /mcp  │
                                    └──────────────┬───────────────┘
                                                   │ one per connection
                                    ┌──────────────▼───────────────┐
                                    │ HardcoverConnection (DO)     │
                                    │  Hardcover tokens            │
                                    │  Effect McpServer + tools    │
                                    └──────────────┬───────────────┘
                                                   │ OAuth + GraphQL
                                    ┌──────────────▼───────────────┐
                                    │ Hardcover API                │
                                    └──────────────────────────────┘

The Worker is an OAuth authorization server for MCP clients, built on @cloudflare/workers-oauth-provider. It supports dynamic client registration and Client ID Metadata Documents.

The Worker checks each /mcp request (token, allowlist, the server's own rate limit, scopes) and forwards it to the connection's Durable Object. The object runs Effect's MCP server. It speaks the sessionless 2026-07-28 revision as well as 2025-11-25, 2025-06-18, and 2025-03-26. Sessions for the 2025 revisions live in the object's memory. When Cloudflare evicts an idle object, its sessions end: the client gets a 404 and, as the protocol requires, starts a new session.

Tools

Kinds: read, write (adds or changes data), and delete. A tool appears only if you chose its scopes for your connection.

Tool

What it does

Kind

Scopes

Needs

hardcover_me

Get your Hardcover profile

read

read:me:content

hardcover_get_user

Look up a reader

read

read:users

hardcover_list_follows

List follows

read

read:social

hardcover_follow_user

Follow a reader

write

write:social, read:users

hardcover_unfollow_user

Unfollow a reader

delete

write:social, read:users

hardcover_list_notifications

List notifications

read

read:notifications

hardcover_mark_notifications_read

Mark notifications read

write

write:notifications

hardcover_search

Search Hardcover

read

read:catalog

hardcover_get_book

Get a book

read

read:catalog

hardcover_get_editions

Get editions

read

read:catalog

hardcover_get_author

Get an author

read

read:catalog

hardcover_get_series

Get a series

read

read:catalog

hardcover_trending_books

Trending books

read

read:catalog

hardcover_list_vibes

List your vibes

read

read:vibes

hardcover_create_vibe

Create a vibe

write

write:vibes

Supporter

hardcover_list_library

List your library

read

read:library

hardcover_currently_reading

Currently reading

read

read:library

hardcover_list_reviews

List your reviews

read

read:library

hardcover_get_library_entry

Get your entry for a book

read

read:library

hardcover_set_status

Set reading status

write

write:library, read:library

hardcover_update_progress

Update reading progress

write

write:library, read:library

hardcover_mark_finished

Mark a book finished

write

write:library, read:library

hardcover_rate_book

Rate a book

write

write:library, read:library

hardcover_write_review

Write a review

write

write:library, write:reviews, read:library

hardcover_delete_review

Delete a review

delete

write:library, write:reviews, read:library

hardcover_update_library_entry

Edit your entry for a book

write

write:library, read:library

hardcover_set_owned

Mark an edition owned

write

write:library, read:lists, write:lists

hardcover_remove_from_library

Remove a book from your library

delete

write:library, read:library

hardcover_add_read

Add a reading session

write

write:library, read:library

hardcover_update_read

Edit a reading session

write

write:library, read:library

hardcover_delete_read

Delete a reading session

delete

write:library, read:library

hardcover_list_journal

List journal entries

read

read:journal

hardcover_add_journal_entry

Add a journal entry

write

write:library

hardcover_update_journal_entry

Edit a journal entry

write

write:library

hardcover_delete_journal_entry

Delete a journal entry

delete

write:library

hardcover_list_lists

List your lists

read

read:lists

hardcover_get_list

Get a list

read

read:lists, read:catalog

hardcover_create_list

Create a list

write

write:lists

hardcover_update_list

Edit a list

write

write:lists, read:lists

hardcover_delete_list

Delete a list

delete

write:lists, read:lists

hardcover_add_to_list

Add a book to a list

write

write:lists

hardcover_remove_from_list

Remove a book from a list

delete

write:lists, read:lists

hardcover_reorder_list

Reorder a list

write

write:lists, read:lists

hardcover_list_goals

List your reading goals

read

read:goals

hardcover_create_goal

Create a reading goal

write

write:goals

hardcover_update_goal

Edit a reading goal

write

write:goals, read:goals

hardcover_delete_goal

Delete a reading goal

delete

write:goals, read:goals

hardcover_find_operations

Find Hardcover API operations

read

none

hardcover_describe_type

Describe a Hardcover GraphQL type

read

none

hardcover_query

Run a Hardcover GraphQL query

read

none

hardcover_mutate

Run a Hardcover GraphQL mutation

write

any write:* scope

Supporter for write:vibes

hardcover_delete

Run a Hardcover GraphQL deletion

delete

any write:* scope

Supporter for write:vibes

hardcover_catalog_edit

Add to or edit the Hardcover catalog

write

any write:* catalog scope

Librarian for write:catalog:edit, Librarian (book_mapper) for write:catalog:map

Supporter is a paid Hardcover membership and Librarian a Hardcover librarian role. Hardcover enforces both; a tool that always needs one says so in its title and description. Sign-in drops write:catalog:edit and write:catalog:map from accounts without the role, but anyone can add catalog records with write:catalog:append.

The raw tools check each document's operation kind, root fields, needed scopes, and size (at most 10 top-level fields) before sending it. They also reject text operators Hardcover has disabled, such as _like and _regex. Mistakes come back as clear errors instead of using up your Hardcover rate limit. hardcover_find_operations and hardcover_describe_type search an index built from Hardcover's API docs. hardcover_find_operations ranks operations by how well their names and return types match, so a phrase like "add a book to a list" works. For a type name that doesn't exist, hardcover_describe_type suggests the closest ones, so UserBook points to user_books.

Hardcover's rate limits are per user, and every app shares them. Each user gets 60 requests a minute (bursts of 10, or 15 for Supporters) and 5,000 a day (50,000 for Supporters). Each top-level field costs one request.

Deploy your own

You need mise, a Cloudflare account, and a Hardcover account. A custom domain is optional; without one, the server lives at https://hardcover-oauth-mcp.<your-subdomain>.workers.dev.

1. Install

git clone https://github.com/benjuntilla/hardcover-oauth-mcp
cd hardcover-oauth-mcp
mise install
cp .env.example .env

2. Register a Hardcover app

Create one at hardcover.app/account/developer-apps/new:

  • Application type: Web app (server-side). You can't change this later.

  • Redirect URIs: https://<your-domain>/callback, plus http://localhost:1337/callback for local runs.

  • Scopes this app may request: read:me:content read:me:roles read:catalog read:library write:library write:reviews read:journal read:lists write:lists read:goals write:goals read:users read:social write:social read:notifications write:notifications read:prompts write:prompts read:vibes write:vibes read:account write:catalog:append write:catalog:edit write:catalog:map openid offline_access. Leave all unticked, since it would also cover scopes Hardcover adds later.

  • Device Authorization Grant: off.

Put the client id and secret into .env as HARDCOVER_CLIENT_ID and HARDCOVER_CLIENT_SECRET. Hardcover shows the secret only once.

3. Configure

In alchemy.run.ts, edit DEPLOYMENTS. Each key is a stage: mise run deploy --stage prod uses prod, and mise run dev uses local.

const DEPLOYMENTS: Readonly<Record<string, DeploymentSettings>> = {
  local: { allowedUsers: ["*"] },
  prod: { allowedUsers: ["your-username"], domain: "hardcover.example.com" },
}
  • allowedUsers: your Hardcover username (or several, or numeric ids). Use "*" to let anyone connect, as the public instance does. Every person uses their own account and Hardcover rate limit.

  • domain: a hostname on a zone in your Cloudflare account. Leave it out to use the auto-assigned workers.dev URL.

4. Sign Alchemy in to Cloudflare

bun alchemy profile edit --add Cloudflare

5. Deploy

mise run deploy --stage prod

This builds the site, creates the Cloudflare resources, and prints the URL. Run it again after changes. mise run logs --stage prod tails logs. mise run destroy --stage prod removes everything.

Deploys keep Alchemy's state in your Cloudflare account, so any machine signed in with Alchemy can redeploy or destroy. The first deploy sets up the state store there. mise run dev and the tests keep theirs in .alchemy/.

  • Plan: use Workers Paid. A connection's Durable Object builds its MCP server when it wakes. That takes about 100 ms of CPU, ten times the Free plan's per-request limit. After that, a call takes about 5 ms.

  • The server's own rate limits: 10 registrations, 30 sign-in steps, and 60 token requests a minute per client IP. Each Hardcover account gets 120 MCP requests a minute.

  • Observability: Workers Logs, Traces, and Issues are on. Cloudflare's request logs record each request's path, status, headers, and client IP, but not its query string or body. Cloudflare redacts the authorization and cookie headers. Leaving out query strings keeps Hardcover's one-time sign-in code out of logs and traces. What the token grants reaches the Durable Object as a method argument rather than a header, so it stays out of the logs. The OAuth provider files grants under a keyed pseudonym of the Hardcover user id, so the storage keys in traces don't reveal it. The Worker logs unexpected failures (defects) without tokens or request data, and Issues groups them. Expected ones, such as Hardcover rate limits, revoked access, or bad queries, go back to the agent as tool errors.

6. Connect a client

Connect the same way as the public instance, with https://<your-domain>/mcp as the URL.

Run locally

With the app and .env from steps 1 and 2 above, the whole flow works on your machine:

  1. Run mise run dev. It serves the Worker in workerd at http://localhost:1337, with local KV and Durable Objects, and reloads on code changes. It builds the static pages (README.md, PRIVACY.md, TERMS.md, SECURITY.md, and site/) once at start, so restart it to see changes to them. You don't need a Cloudflare account.

  2. Connect a client on the same machine to http://localhost:1337/mcp, for example claude mcp add --transport http hardcover-local http://localhost:1337/mcp.

Development

mise run check      # format check, lint, prose lint, unused code, typecheck (bun check), and unit tests
mise run test:e2e   # the Worker in workerd, a mock Hardcover, and a scripted MCP client
  • Unit tests (bun test) cover the GraphQL guard, the executor's refresh and retry rules, scope handling, and every tool. Each tool runs through the real Effect MCP server, and the tests validate its GraphQL against Hardcover's published schema (test/fixtures/hardcover-schema.graphql).

  • The end-to-end test runs the Worker in workerd against a mock Hardcover, signing in and calling tools as an MCP client.

  • The README tool table comes from the toolkit (mise run docs:tools), and a unit test fails when it's stale.

  • The schema index behind hardcover_find_operations and hardcover_describe_type comes from Hardcover's API docs (mise run schema:sync).

  • Vale lints the prose on the site's pages with its standard style, Std (mise run lint:prose).

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    C
    maintenance
    Enables management of Micro.blog book collections through natural language, allowing users to organize bookshelves, add/move books, and track reading goals. Built with FastMCP for reliable integration with Claude Desktop.
    11
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Connects AI assistants to the Hardcover book library, enabling natural language book searches, reading status updates, list management, and library exploration.
    28
    47 PyPI
    9
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP-compatible AI assistants to search the Hardcover book catalogue and manage personal library data, reading progress, reading statistics, goals, activities, and more through natural language.
    25
    1
    MIT