About MTG Assistant
MTG Assistant is an MCP server for players and others looking up Magic: The Gathering cards. It queries Scryfall for card details, which can also support research for rules questions.
Key features
- 01Search card details through Scryfall
- 02Query by name or characteristics
- 03Use card lookups as rules-question context
Use cases
- 01Check details for a specific card
- 02Find a card using partial information
- 03Gather card data for a rules question
MCP support
The MCP server exposes the get_mtg_card_info tool, which accepts a query string to retrieve Magic: The Gathering card details from Scryfall.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Server MTG Assistant
A Model Context Protocol server that provides Magic: The Gathering card information fetching capabilities using the Scryfall API.
Example Rules Question Workflow
While primarily used for looking up specific card details, this server can also be a crucial first step in answering MTG rules questions.
User Query: "If I cast a Finale of Devastation with X=10 and search for an Avenger of Zendikar, do the tokens also get +10/+10 and haste, or not?"
Available Tools
get_mtg_card_info- Retrieves details for a specific Magic: The Gathering card from Scryfall.query(string, required): The search query string (e.g., card name, partial name, characteristics).
Installation and Running
This project uses uv for dependency management and running scripts.
Using uv (recommended)
Ensure uv is installed. You can run the server directly from the project directory:
# Navigate to the project root directory first
cd path/to/mcp-servers/mcp-mtg-assistant
# Install dependencies (if needed) and run the server script
uv run mcp-server-mtg-assistant
Using PIP (for distribution or alternative setup)
If the package were published, you could install it via pip:
pip install mcp-server-mtg-assistant
After installation, you could run it as a script:
python -m mcp_server_mtg_assistant
For development, you typically run it using uv run as shown above.
Configuration
Configure for MCP Clients (e.g., Claude.app, Inspector)
Add an entry to your client's MCP server configuration. The exact key ("mtg-assistant" in the examples) can be chosen by you.
Important: The configuration needs to point uv to the correct project directory using the --directory argument. The path style (/ vs \) depends on your operating system and how you run uv.
Default: Using uv Directly (Linux/macOS/WSL)
This is the standard approach if your MCP client and the server run in the same Linux, macOS, or WSL environment.
// Example for mcp.json or Claude settings
"mcpServers": {
"mtg-assistant": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-servers/mcp-mtg-assistant", // Unix-style path
"run",
"mcp-server-mtg-assistant"
]
}
}
Windows Client + WSL Server
This configuration is recommended if your MCP client runs on Windows, but you want the server to execute within WSL It uses wsl.exe to invoke uv inside WSL.
Requirements:
uvmust be installed inside your WSL distribution.- Adjust the path to
uvinside WSL (e.g.,/home/user/.cargo/bin/uv) if it's not in the WSLPATH. - Use the
/mnt/...style path for the--directoryargument accessible from within WSL.
// Example for mcp.json or Claude settings on Windows
"mcpServers": {
"mtg-assistant": {
"command": "wsl.exe",
"args": [
"/home/your-user/.cargo/bin/uv", // uv WSL PATH
"--directory",
"/mnt/d/repos/mcp-servers/mcp-mtg-assistant", // WSL-style path to project
"run",
"mcp-server-mtg-assistant"
]
}
}
Alternative: Using uv Directly on Windows
This assumes uv is installed directly on Windows and your MCP client also runs directly on Windows.
- Use the Windows-style path (
D:\...) for the--directoryargument. - Be mindful of potential
.venvconflicts if you also use WSL (see below).
// Example for mcp.json or Claude settings on Windows
"mcpServers": {
"mtg-assistant": {
"command": "uv",
"args": [
"--directory",
"D:\path\to\mcp-servers\mcp-mtg-assistant", // Windows-style path
"run",
"mcp-server-mtg-assistant"
]
}
}
Handling .venv Conflicts (Different Environments)
- Problem:
uv runcreates a.venvdirectory specific to the operating system/environment (e.g., Linux vs. Windows). If you switch between running the server directly on Windows and running it via WSL (or native Linux), the existing.venvmight be incompatible. - Solution: Before switching environments, delete the
.venvdirectory in themcp-mtg-assistantproject root.uv runwill then create a fresh, compatible one for the environment you are using.
Debugging
You can use the MCP inspector to debug the server by prefixing the command and arguments from your configuration with npx @modelcontextprotocol/inspector.
# Example using the Default (Linux/macOS/WSL) configuration:
npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-servers/mcp-mtg-assistant run mcp-server-mtg-assistant
# Example using the Recommended (Windows Client + WSL Server) configuration:
npx @modelcontextprotocol/inspector wsl.exe /home/your-user/.cargo/bin/uv --directory /mnt/d/repos/mcp-servers/mcp-mtg-assistant run mcp-server-mtg-assistant
# Example using the Alternative (Direct Windows) configuration:
npx @modelcontextprotocol/inspector uv --directory D:\path\to\mcp-servers\mcp-mtg-assistant run mcp-server-mtg-assistant
Contributing
We encourage contributions to help expand and improve this MTG Assistant MCP server. Whether you want to add new features, enhance existing functionality, or improve documentation, your input is valuable.
For examples of other MCP servers and implementation patterns, see: https://github.com/modelcontextprotocol/servers
Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements.
License
mcp-server-mtg-assistant is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.
Comments
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.