dtrpg-mcp
Enables searching your DriveThruRPG library and the public catalog for tabletop RPG products, returning structured details like title, description, publisher, and game system.
README
dtrpg-mcp
An MCP server that lets an LLM search your DriveThruRPG library and the public DriveThruRPG catalog for tabletop RPG products, returning structured details (title, description, publisher, authors, game system, and DriveThruRPG product id) for each match.
It speaks MCP over stdio and exposes two tools: search_library (your
purchased products) and search_products (the general public catalog).
Requirements
- Python >= 3.12
- A DriveThruRPG Application Key (see Getting an API key below)
Installation
pip install dtrpg-mcp
or, to run it without installing anything permanently:
uvx dtrpg-mcp
Configuration
The server needs one environment variable:
| Variable | Required | Description |
|---|---|---|
DTRPG_API_KEY |
Yes | Your DriveThruRPG Application Key, used to authenticate against the API. |
You can set it directly in your shell/MCP client config, or drop a .env
file next to your project (the server walks up from its own install
location looking for .env, so a .env in your working directory or a
parent of it will be picked up automatically via python-dotenv).
Getting a DriveThruRPG API key
- Log in to drivethrurpg.com.
- Go to My Account -> Application Keys (or open
https://www.drivethrurpg.com/en/account/application-keysdirectly). - Click Generate New Key, give it a name (e.g. "dtrpg-mcp"), and create it.
- Copy the generated key — this is your
DTRPG_API_KEY.
The key only grants access to your library and to the public product catalog search; it does not expose your payment details or let anything make purchases on your behalf.
Using it with an MCP client
Add it to your client's MCP server config. For example, in Claude Desktop's
claude_desktop_config.json:
{
"mcpServers": {
"dtrpg": {
"command": "uvx",
"args": ["dtrpg-mcp"],
"env": {
"DTRPG_API_KEY": "your-application-key-here"
}
}
}
}
If installed via pip instead of uvx, use "command": "dtrpg-mcp" with
no args.
Tools
Both tools return a list of product detail objects with the same shape:
| Field | Description |
|---|---|
product_id |
The DriveThruRPG product id. |
order_product_id |
The id of your specific purchased order/product; null for search_products results (not necessarily owned). |
title |
Product title. |
description |
A short description/blurb of the product. |
publisher |
Publisher name. |
authors |
List of author names (only populated by search_products — DriveThruRPG's library endpoint does not include author data). |
game_system |
Game system tag, when DriveThruRPG's API surfaces one for the product; otherwise null. |
search_library
Search products you've already purchased in your DriveThruRPG library.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
query |
string | — | Text to match against product titles (case-insensitive substring match). |
max_values |
integer | 10 |
Maximum number of results to return. |
Example call — anything in your library with "dungeon" in the title:
{"query": "dungeon"}
Performance note: DriveThruRPG's library endpoint has no server-side title filter and is capped at 50 items per page, with each page taking several seconds to return. A query that matches nothing (or matches only late in a large library) can take tens of seconds to resolve, since pages are fetched in concurrent batches rather than one huge request. This is a limitation of the underlying API, not something a client-side change can fully eliminate.
search_products
Search the general public DriveThruRPG catalog for products — not limited to your library, so this also finds things you don't own.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
query |
string | — | Text to match against product titles (keyword match). |
max_values |
integer | 10 |
Maximum number of results to return. |
Example call — search the catalog for "bardo", capped to 5 results:
{"query": "bardo", "max_values": 5}
Notes on the DriveThruRPG API
DriveThruRPG does not publish official API documentation. This client's
endpoint usage was reverse-engineered from the community projects
glujan/drpg and
quickwick/drivethrurpg-calibre-plugin,
and verified empirically against the live API. Notably, the per-product
detail endpoint (GET products/{id}) returns 403 for Application Keys
like the one this tool uses (it appears to require a different auth scope),
so search_library and search_products build product details from the
library (order_products) and catalog search (products) list endpoints
instead, both of which work with a standard Application Key.
Development
uv sync
uv run pytest
Run the server directly for manual/stdio testing:
uv run dtrpg-mcp
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.