FoundryVTT MCP Server

FoundryVTT MCP Server

A Model Context Protocol server that integrates with FoundryVTT, allowing AI assistants to interact with tabletop gaming sessions through natural language to query actors, roll dice, generate content, and manage game worlds.

Category
Visit Server

README

FoundryVTT MCP Server

A Model Context Protocol (MCP) server that integrates with FoundryVTT, allowing AI assistants to interact with your tabletop gaming sessions. Query actors, roll dice, generate content, and manage your game world through natural language.

Features

Core Functionality

  • 🎲 Dice Rolling - Roll dice with standard RPG notation
  • 🔍 Data Querying - Search actors, items, scenes, and journal entries
  • 📊 Game State - Access current scene, combat status, and world information
  • 🎭 Content Generation - Generate NPCs, loot, and random encounters
  • 📝 Rule Lookup - Query game rules and mechanical information

Real-time Integration

  • 🔄 Live Updates - WebSocket connection for real-time game state
  • ⚔️ Combat Management - Track initiative and combat state
  • 👥 User Awareness - See who's online and their status

AI-Powered Features

  • 🧠 Tactical Suggestions - Get combat advice and strategy tips
  • 🎪 Story Assistance - Generate plot hooks and narrative elements
  • 🎨 World Building - Create locations, NPCs, and quests on demand

Installation

Prerequisites

  • Node.js 18+
  • FoundryVTT server running and accessible
  • MCP-compatible AI client (Claude Desktop, etc.)

Setup

  1. Clone and install:
git clone <repository-url>
cd foundry-mcp-server
npm install
  1. Configure environment:
cp .env.example .env
# Edit .env with your FoundryVTT details
  1. Required environment variables:
FOUNDRY_URL=http://localhost:30000
FOUNDRY_API_KEY=your_api_key_here
# OR use username/password:
FOUNDRY_USERNAME=your_username
FOUNDRY_PASSWORD=your_password
  1. Build and start:
npm run build
npm start

Development Mode

npm run dev

FoundryVTT Configuration

Option 1: API Key (Recommended)

  1. In FoundryVTT, go to Settings → Configure Settings
  2. Enable "Enable API Access"
  3. Generate an API key for external access
  4. Add the key to your .env file

Option 2: Username/Password

  1. Ensure your FoundryVTT user has appropriate permissions
  2. Add credentials to .env file
  3. The server will authenticate automatically

Permissions Required

Your FoundryVTT user needs these permissions:

  • View actors, items, scenes, and journals
  • Create and modify journal entries (for content generation)
  • Access compendium data
  • Use dice rolling API

Usage

Basic Queries

Ask your AI assistant things like:

Dice Rolling:

  • "Roll 1d20+5 for an attack roll"
  • "Roll 4d6 drop lowest for ability scores"
  • "Roll 2d10+3 for damage"

Game Data:

  • "Show me all the NPCs in this scene"
  • "Find magic weapons in the party's inventory"
  • "What's the current combat initiative order?"
  • "Search for healing potions"

Content Generation:

  • "Generate a random NPC merchant"
  • "Create loot for a CR 5 encounter"
  • "Generate a tavern with NPCs and plot hooks"

Advanced Features

Rule Lookups:

  • "Look up the grappling rules"
  • "How does the Fireball spell work?"
  • "What are the conditions for being frightened?"

Tactical Advice:

  • "Suggest tactics for fighting a dragon"
  • "What should our wizard do this turn?"
  • "Analyze this combat encounter"

World Building:

  • "Create a mysterious forest location"
  • "Generate a side quest involving missing merchants"
  • "Design a magic item appropriate for level 8 characters"

Available Tools

Data Access

  • search_actors - Find characters, NPCs, monsters
  • search_items - Find equipment, spells, consumables
  • search_journals - Search notes and handouts
  • get_scene_info - Current scene details
  • get_actor_details - Detailed character information

Game Mechanics

  • roll_dice - Roll dice with any formula
  • update_actor_hp - Modify character health
  • get_combat_status - Combat state and initiative
  • lookup_rule - Game rules and spell descriptions

Content Generation

  • generate_npc - Create random NPCs
  • generate_loot - Create treasure appropriate for level
  • roll_table - Random encounters, events, weather
  • suggest_tactics - Combat advice and strategy

Available Resources

The server exposes these FoundryVTT resources:

  • foundry://world/info - World and campaign information
  • foundry://world/actors - All actors in the world
  • foundry://scene/current - Current active scene
  • foundry://combat/current - Active combat state
  • foundry://compendium/spells - Spell database
  • foundry://compendium/monsters - Monster database

Configuration

Server Settings

Edit .env to customize:

# Logging
LOG_LEVEL=info  # debug, info, warn, error

# Performance
FOUNDRY_TIMEOUT=10000      # Request timeout (ms)
FOUNDRY_RETRY_ATTEMPTS=3   # Retry failed requests
CACHE_TTL_SECONDS=300      # Cache data for 5 minutes

Security

  • Use API keys instead of passwords when possible
  • Limit FoundryVTT user permissions to minimum required
  • Run server on internal network only
  • Monitor logs for suspicious activity

Troubleshooting

Connection Issues

# Test FoundryVTT connection
curl http://localhost:30000/api/status

# Check server logs
npm run dev  # Shows detailed logging

Common Problems

"Failed to connect to FoundryVTT"

  • Verify FOUNDRY_URL is correct
  • Check if FoundryVTT is running
  • Ensure API access is enabled

"Authentication failed"

  • Verify API key or username/password
  • Check user permissions in FoundryVTT
  • Ensure user is not banned/restricted

"Tool not found" errors

  • Update to latest server version
  • Check tool name spelling
  • Review available tools in logs

Development

Project Structure

src/
├── config/           # Configuration management
├── foundry/          # FoundryVTT client and types
├── tools/            # MCP tool definitions
├── resources/        # MCP resource definitions
├── utils/            # Utilities and logging
└── index.ts          # Main server entry point

Adding New Tools

  1. Define tool schema in src/tools/index.ts
  2. Add handler method in src/index.ts
  3. Implement FoundryVTT API calls in src/foundry/client.ts
  4. Add TypeScript types in src/foundry/types.ts
  5. Test with your AI assistant

Testing

# Run tests
npm test

# Run with coverage
npm run test:coverage

# Lint code
npm run lint

Building

# Development build
npm run build

# Clean build
npm run clean && npm run build

API Reference

Environment Variables

Variable Required Description Default
FOUNDRY_URL FoundryVTT server URL -
FOUNDRY_API_KEY API key for authentication -
FOUNDRY_USERNAME Username (if no API key) -
FOUNDRY_PASSWORD Password (if no API key) -
LOG_LEVEL Logging verbosity info
NODE_ENV Environment mode development
FOUNDRY_TIMEOUT Request timeout (ms) 10000
FOUNDRY_RETRY_ATTEMPTS Retry failed requests 3
CACHE_TTL_SECONDS Cache duration 300

⭐ Either API key OR username/password required

Tool Schemas

roll_dice

{
  "formula": "1d20+5",
  "reason": "Attack roll against goblin"
}

search_actors

{
  "query": "goblin",
  "type": "npc",
  "limit": 10
}

generate_npc

{
  "race": "human",
  "level": 5,
  "role": "merchant",
  "alignment": "neutral good"
}

Integration Examples

Claude Desktop Configuration

Add to your Claude Desktop MCP settings:

{
  "mcpServers": {
    "foundry": {
      "command": "node",
      "args": ["/path/to/foundry-mcp-server/dist/index.js"],
      "env": {
        "FOUNDRY_URL": "http://localhost:30000",
        "FOUNDRY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Custom MCP Client

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';

const transport = new StdioClientTransport({
  command: 'node',
  args: ['./dist/index.js']
});

const client = new Client({
  name: "foundry-client",
  version: "1.0.0"
}, {
  capabilities: {}
});

await client.connect(transport);

// Roll dice
const result = await client.request({
  method: "tools/call",
  params: {
    name: "roll_dice",
    arguments: {
      formula: "1d20+5",
      reason: "Initiative roll"
    }
  }
});

Roadmap

Version 0.2.0

  • [ ] Combat management tools (start/end combat, advance initiative)
  • [ ] Token manipulation (move, update status effects)
  • [ ] Scene navigation and switching
  • [ ] Playlist controls and ambient audio

Version 0.3.0

  • [ ] Character sheet editing (level up, add equipment)
  • [ ] Journal entry creation and editing
  • [ ] Macro execution and management
  • [ ] Advanced content generation (dungeons, NPCs with full stats)

Version 1.0.0

  • [ ] Multi-world support
  • [ ] User permission management
  • [ ] Webhook support for external triggers
  • [ ] Performance optimization and caching
  • [ ] Full test coverage
  • [ ] Docker deployment

Documentation

Complete API documentation is available in the docs/ directory, auto-generated from TypeScript source code and JSDoc comments.

📖 Viewing Documentation

Local development:

npm run docs        # Generate documentation
npm run docs:serve  # Generate and serve locally

Online: Browse the docs/ folder in this repository or visit the GitHub Pages site (if enabled).

📚 What's Documented

  • FoundryClient API - Complete client documentation with examples
  • TypeScript Interfaces - All data structures and type definitions
  • Configuration - Environment variables and setup options
  • Utilities - Helper functions and logging
  • Usage Examples - Code samples for common operations

The documentation is automatically updated via GitHub Actions when source code changes.

Contributing

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes and add tests
  4. Commit: git commit -m 'Add amazing feature'
  5. Push: git push origin feature/amazing-feature
  6. Open a Pull Request

Code Style

  • Use TypeScript strict mode
  • Follow existing naming conventions
  • Add JSDoc comments for public APIs
  • Write tests for new functionality
  • Use meaningful commit messages

License

MIT License - see LICENSE file for details.

Support

Acknowledgments

  • FoundryVTT team for the excellent VTT platform
  • Anthropic for the Model Context Protocol
  • The tabletop gaming community for inspiration and feedback

Happy Gaming! 🎲

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