hardcover-mcp
Hardcover
Documentation
Hardcover MCP
A Model Context Protocol (MCP) server that exposes read-only access to the Hardcover.app GraphQL API. Tools are namespaced under `books.*`, `users.*`, and `series.*`, with resources and prompts to guide safe, low-volume querying.
This is an unofficial, community-maintained server and is not affiliated with Hardcover.app.
Requirements
- Python 3.11+
- A Hardcover API key (read-only Bearer token) from https://hardcover.app/account/api
Installation
# Option A: with uv (recommended)
uv pip install -e .
# Option B: with pip
python -m venv .venv
source .venv/bin/activate
pip install -e .Transport Protocol
This server currently only supports STDIO as the transport protocol
Usage
1) Get an API key from https://hardcover.app/account/api. Copy the value exactly as provided (it already starts with `Bearer `).
2) Export it for the server:
export HARDCOVER_API_KEY="Bearer "Running the server directly
3) Start the MCP server:
uv run src/hardcover_mcp/main.pyConfiguring STDIO for a AI chat
Codex
[mcp_servers.hardcover_mcp]
command = "uv"
args = ["run", "src/hardcover_mcp/main.py"]
env = { "HARDCOVER_API_KEY" = "API KEY heRE" }
cwd = "full_path_to/hardcover_mcp"The server registers the `books.*`, `users.*`, and `series.*` tool namespaces, plus resources like `hardcover/tag-categories` and usage prompts such as `hardcover/fantasy-this-year`.
Running the test suite
pytestTroubleshooting
- `HARDCOVER_API_KEY environment variable is required`: ensure the variable is set in the same shell you start the server. Include the leading `Bearer ` prefix.
- `Hardcover API returned an error response` or 401/403: confirm the token is valid and not expired.
- Slow responses or timeouts: reduce `limit`/`offset` arguments; the API enforces rate limits. Start with `limit<=10`.
- SSL/HTTP transport issues: check local network/proxy settings and retry with a stable connection.
Frequently asked questions
What is hardcover-mcp?
hardcover-mcp is Hardcover
How do I install hardcover-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is hardcover-mcp open source?
Yes — it is hosted on GitHub at https://github.com/AlexSowT/hardcover-mcp and has 1 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP