Hardcover Mcp
About
hardcover-mcp connects your Hardcover library to AI assistants like Claude and Copilot. Search for books, update your reading status, manage lists, explore series — all through natural conversation instead of clicking through menus.
Details
- Author
- kristianedlund
- Downloads
- 279
- Categories
- Other, Knowledge Base, Database, Search, AI
Jump to
- Library tracking — reading status, ratings, and dates
- List management — create, edit, add, and remove books
- Book discovery — search books, authors, series, and editions
- Account info — profile and reading statistics
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Hardcover McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
You control your own API key, which stays on your machine and is never shared with third parties. The server runs locally through your MCP client, and actions only occur when explicitly requested.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"hardcover mcp": {
"hardcover": {
"command": "uvx",
"args": [
"hardcover-mcp"
],
"env": {
"HARDCOVER_API_TOKEN": "<your token>"
}
}
}
}
}McpServers
{
"hardcover": {
"command": "uvx",
"args": [
"hardcover-mcp"
],
"env": {
"HARDCOVER_API_TOKEN": "<your token>"
}
}
}Talk to yourHardcoverlibrary from any AI assistant.
hardcover-mcp connects yourHardcoverlibrary to AI assistants like Claude and Copilot. Search for books, update your reading status, manage lists, explore series — all through natural conversation instead of clicking through menus.
"What's on my currently reading list?"
"Add Project Hail Mary to my library as currently reading"
"Search for books by Brandon Sanderson"
"Create a list called 'Summer Reading' and add The Hobbit to it"
"Show me the Stormlight Archive series in reading order"
"Move Project Hail Mary and The Martian to currently reading"
"What books has Andy Weir written? Add any I haven't read to my want-to-read list"
"Compare my rating of Dune with the Hardcover average"
- Library tracking— status, ratings, reading dates
- List management— create, edit, add/remove books
- Discovery— search books, authors, series, editions, and more
- Account info— your profile and reading stats
- You control your API key— it stays on your machine, never shared with third parties
- Runs locallythrough your MCP client — no external server involved
- Actions only happen when explicitly requested— nothing runs in the background
- You review prompts and outputsin your client before anything is sent
- Installuv(a fast Python package runner — the setup takes seconds).
- Get an API token fromhardcover.app/account/api.
- Add the config below to your MCP client — no manual install needed,uvxhandles it.
{ "servers": { "hardcover": { "command": "uvx", "args": ["hardcover-mcp"], "env": { "HARDCOVER_API_TOKEN": "<your token>" } } } }
{ "mcpServers": { "hardcover": { "command": "uvx", "args": ["hardcover-mcp"], "env": { "HARDCOVER_API_TOKEN": "<your token>" } } } }
git clone https://github.com/kristianedlund/hardcover-mcp.git cd hardcover-mcp uv sync
uv run ruff check src/ uv run ruff format --check src/
Integration tests hit the live Hardcover API and require a valid token. They areskipped automaticallyin CI and when the token is absent.
To run them locally, create a.envfile with your token:
Write tests follow a create → verify → delete lifecycle so the account is left unchanged.
- Open an issue first to discuss the change.
- Fork the repo and create a branch (feature/short-descriptionorfix/short-description).
- Run lint and tests before submitting:
uv run ruff check src/ uv run ruff format --check src/ uv run pytest tests/ -v
The Hardcover API allows 60 requests per minute. The server handles this automatically — it queues requests and retries if needed. You shouldn't hit this in normal use.
Unofficial project. Not affiliated withHardcover.
Extracts document content from Microsoft Learn and GitHub URLs and stores it in PocketBase for retrieval and search.
Domain intelligence tools - NS reverse lookup, newly registered domain search and more
An MCP server for interacting with FHIR (Fast Healthcare Interoperability Resources) servers, enabling access and search of healthcare data.
Interact with on-disk documents using agentic RAG and hybrid search via LanceDB.
Romanian business registry lookup (official ONRC data), director search, website contact extraction, and WHOIS/DNS/SPF-DMARC domain audit for AI agents.
MCP server for Manticore Search — query and manage search database
Search MeiliSearch indexes and manage documents via AI agents
A serverless NoSQL database and search platform.
Access Turkish legal databases and decision sources through a standardized MCP server.
Zillow Data API MCP server — 4 tools: property lookup by address, lookup by ZPID, Zestimate, and listing search. 300+ fields per home across 160M+ U.S. parcels in one REST call. Free tier: 100 credits, no card. Corrected re-submission of the existing api.zillapi.com/mcp listing (was 'nine tools', now 4).
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
