Flesh and Blood Card Database MCP Server

Flesh and Blood Card Database MCP Server

MCP server for searching Flesh and Blood TCG cards, retrieving print variations, and browsing product catalogs via the CardVault API.

Category
Visit Server

README

Flesh and Blood Card Database MCP Server

A Model Context Protocol (MCP) server for searching and retrieving information about Flesh and Blood Trading Card Game (FAB TCG) cards. This server is deployed on Cloudflare Workers and provides tools for card search and print variation lookup.

CardVault API Migration Status

The official FAB card database has moved to cardvault.fabtcg.com and uses a new API host (api.cardvault.fabtcg.com).

  • Analysis date: 2026-03-07
  • Investigation + migration design: docs/cardvault-api-analysis.md
  • Implementation status: search_fab_cards / get_fab_card_prints / get_card_detail / get_fab_products now use CardVault API (api.cardvault.fabtcg.com)

Features

This MCP server provides the following tools:

1. Card Search (search_fab_cards)

Search for Flesh and Blood cards by name. Returns detailed information about matching cards, including:

  • Card ID and name
  • Card images
  • Card attributes (pitch, cost, power, defense)
  • Card text and type information
  • Links to the official card page

2. Print Variations Lookup (get_fab_card_prints)

Retrieve all print variations of a specific card using its card ID. Returns information such as:

  • Print ID and associated card ID
  • Print name and display name
  • Print images (small, normal, large sizes)
  • Layout information
  • Finish types available

3. Product Catalog Lookup (get_fab_products)

Retrieve product groups shown on cardvault.fabtcg.com/products, including:

  • Product group name and type
  • Release dates
  • Nested product entries (slug, language, printed date)
  • Pagination metadata (next, previous, nextPage, previousPage)

Deployment

This project is designed to be deployed on Cloudflare Workers.

Prerequisites

  • Node.js and npm installed
  • Cloudflare account
  • Wrangler CLI installed (npm install -g wrangler)

Deployment Steps

  1. Clone this repository:

    git clone <repository-url>
    cd fab-card-db-mcp
    
  2. Install dependencies:

    npm install
    
  3. Authenticate with Cloudflare:

    wrangler login
    
  4. Deploy to Cloudflare Workers:

    wrangler deploy
    

The server will be deployed to the domain configured in wrangler.jsonc (currently fab-card-db-mcp.discord.jp).

Using the MCP Server

Endpoints

The server exposes two main endpoints:

  • /sse or /sse/message - SSE-based MCP endpoint
  • /mcp - Regular MCP endpoint

Example Usage

When connected to an MCP client, you can use the provided tools as follows:

Card Search Example

// Using the search_fab_cards tool
const searchResults = await use_mcp_tool({
  server_name: "Flesh and Blood Card Search API",
  tool_name: "search_fab_cards",
  arguments: {
    query: "Awakening"
  }
});

// Results will contain card information matching the search query

Print Variations Example

// Using the get_fab_card_prints tool
const printVariations = await use_mcp_tool({
  server_name: "Flesh and Blood Card Search API",
  tool_name: "get_fab_card_prints",
  arguments: {
    cardId: "CARD_ID_HERE" // Replace with an actual card ID from search results
  }
});

// Results will contain all print variations for the specified card

Connecting with MCP Clients

Claude Desktop

To connect this MCP server to Claude Desktop:

  1. Go to Settings > Developer > Edit Config in Claude Desktop
  2. Update the configuration with:
{
  "mcpServers": {
    "fab-cards": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://fab-card-db-mcp.discord.jp/sse"  // Or your deployed URL
      ]
    }
  }
}
  1. Restart Claude Desktop to access the FAB card search tools

Other MCP Clients

For other MCP clients, configure them to connect to:

  • https://fab-card-db-mcp.discord.jp/sse (for SSE-based connections)
  • https://fab-card-db-mcp.discord.jp/mcp (for regular MCP connections)

License

See the LICENSE file for details.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured