uefn-mcp
MCP server that enables AI assistants to inspect and build Fortnite maps by driving a running Unreal Editor for Fortnite instance via Python, exposing tools for spawning actors, browsing content, and executing editor operations.
README
uefn-mcp
Lets Claude build Fortnite maps for you inside UEFN (Unreal Editor for Fortnite) — placing props, moving things around, browsing your content — instead of you clicking through the editor UI by hand.
What you need first
- UEFN installed, with a project created.
- Claude Code.
That's it — Claude can install everything else itself.
Setup
Open a terminal in this folder, start Claude Code, and paste this:
Install and register the uefn-mcp server with Claude Code: check whether
uvis installed and install it if it's missing, runuv syncin this folder, then runclaude mcp add uefn --scope user -- uv --directory "$(pwd)" run uefn-mcp.
--scope user registers the server globally instead of tying it to this one
folder, so it's also available from other working directories — e.g. a
fortnite-maps notes workspace set up via the fortnite-map-setup skill
(see docs/).
Once that's done, start a new Claude Code session in this folder (MCP servers only connect when a session starts). Then open UEFN with your project loaded and paste this:
Set up my UEFN project for remote execution.
Claude will find your project on disk and turn on the setting UEFN needs (it's off by default). If UEFN was already open, Claude will tell you to restart it — this setting only takes effect on startup.
Once UEFN is back up with your project loaded, you're ready to build.
What to ask Claude to do
Once it's set up, just describe what you want in your own words. For example:
Show me everything currently placed in my level
Spawn a chest at the center of the map
Move the actor called "SpawnPoint_1" up by 200 units
Duplicate "Tree_03" and offset the copy to the side
What props/devices are available in my content browser?
Save the level
If Claude gets stuck because it doesn't know the exact name of a Fortnite device or prop, it can look through your content browser itself to find it — you don't need to know Unreal or Python to use any of this.
Limitations
- Only one UEFN instance can be connected at a time — if you have more than one open, Claude connects to whichever one it finds first.
- Claude finds things you've placed by their name in the World Outliner, so giving actors clear, unique names helps it find the right one.
How it works
See docs/ for a deeper look at the architecture, the wire protocol this talks to UEFN, and a traced example of a tool call end to end.
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.