Foundry VTT MCP Bridge
Connects Claude Desktop to Foundry VTT for AI-powered campaign management, enabling natural language interaction with game data including quest creation, character management, compendium searches, and dice rolling. Provides 20 MCP tools for seamless integration between Claude and your tabletop RPG sessions.
README
Foundry VTT MCP Bridge
Connect Foundry VTT to Claude Desktop for AI-powered campaign management through the Model Context Protocol (MCP).
Overview
The Foundry MCP Bridge enables natural AI conversations with your Foundry VTT game data:
- Quest Creation: Create quests from prompts that incorporate what exists in your world and journals
- Character Management: Query character stats, abilities, and information
- Compendium Search: Find items, spells, and creatures using natural language
- Content Creation: Generate actors, NPCs, and quest journals from simple prompts
- Scene Information: Access current scene data and world details
- Dice Coordination: Interactive roll requests with player targeting
- Campaign Management: Multi-part quest and campaign tracking
This project was built with the assistance of Claude Code. If you like this project, consider supporting it on Patreon.
Installation
Prerequisites
- Foundry VTT v13
- Claude Desktop with MCP support
- Windows (for automated installer) or Node.js 18+ for manual installation
Option 1: Windows Installer (Recommended)
- Download the latest
FoundryMCPServer-Setup.exefrom Releases - Run the installer - it will:
- Install the MCP server with bundled Node.js runtime
- Configure Claude Desktop automatically
- Optionally install the Foundry module to your VTT installation
- Restart Claude Desktop
- Enable "Foundry MCP Bridge" in your Foundry Module Management
Option 2: Manual Installation
Install the Foundry Module
- Open Foundry VTT v13
- Select install module in the Foundry Add-ons menu
- At the bottom of the window, add the Manifest URL as: https://github.com/adambdooley/foundry-vtt-mcp/blob/master/packages/foundry-module/module.json and click install
- Enable "Foundry MCP Bridge" in Module Management
Install the MCP Server
# Clone repository
git clone https://github.com/adambdooley/foundry-vtt-mcp.git
cd foundry-vtt-mcp
# Install dependencies and build
npm install
npm run build
Configure Claude Desktop
Add this to your Claude Desktop configuration (claude_desktop_config.json) file:
{
"mcpServers": {
"foundry-mcp": {
"command": "node",
"args": ["path/to/foundry-vtt-mcp/packages/mcp-server/dist/index.js"],
"env": {
"FOUNDRY_HOST": "localhost",
"FOUNDRY_PORT": "31415"
}
}
}
}
Starting Claude Desktop will start the MCP Server.
Getting Started
- Start Foundry VTT and load your world
- Open Claude Desktop
- Chat with Claude about your currently loaded Foundry World
Example Usage
Once connected, ask Claude Desktop:
- "Show me my character Clark's stats"
- "Find all CR 12 humanoid creatures for an encounter"
- "Create a quest about investigating missing villagers"
- "Roll a stealth check for Tulkas"
- "What's in the current Foundry scene?"
Features
- 20 MCP Tools that allow Claude to interact with Foundry
- Character Management: Access stats, abilities, and inventory
- Enhanced Compendium Search: Instant filtering by CR, type, abilities, and more
- Content Creation: Generate actors, NPCs, and quest journals
- Campaign Management: Multi-part quest tracking with progress dashboards
- Interactive Dice System: Send different dice roll requests to players from Claude
- Actor Ownership: Manage player permissions for characters and tokens
- GM-Only: MCP Bridge only connects to Game Master users
Architecture
Claude Desktop ↔ MCP Protocol ↔ MCP Server ↔ WebSocket ↔ Foundry Module ↔ Foundry VTT
- Foundry Module: Provides secure data access within Foundry VTT
- MCP Server: External Node.js server handling Claude Desktop communication
- No API Keys Required: Uses your existing Claude Desktop subscription
Security & Permissions
- GM-Only Access: All functionality restricted to Game Master users
- Configurable Permissions: Control what data Claude can access and modify
- Session-Based Authentication: Uses Foundry's built-in authentication system
System Requirements
- Foundry VTT: Version 13
- Claude Desktop: Latest version with MCP support
- Claude Pro/Max Plan: Required to connect to MCP servers
- Operating System: Windows 10/11 (installer), or other OSes/manual Windows install with Node.js 18+ (manual)
Support & Development
- Issues: Report bugs on GitHub Issues
- YouTube Channel: Subscribe for updates and tutorials
- Support Development: Support on Patreon
- Documentation: Built with TypeScript, comprehensive documentation included
- License: MIT License
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.