HullForge MCP Connector
Allows Claude to control a running Unreal Engine 5 editor, providing tools for scene manipulation, asset management, and other editor operations through a bridge to the HullForge editor plugin.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@HullForge MCP Connectorlist all actors in the current level"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HullForge MCP connector
The MCP server half of HullForge, which lets Claude drive a running Unreal Engine 5 editor.
MIT licensed. This repository is the connector only.
What this is, and what it is not
HullForge is two programs.
This repository | The connector. Speaks MCP to Claude over stdio, and a length-prefixed JSON protocol to the editor over loopback. MIT licensed. |
The editor plugin | A separate, proprietary Unreal Engine plugin that holds every tool and does all the work. Licensed under its own EULA and distributed via Fab. Not in this repository. |
The connector contains no Unreal Engine logic. It is transport, framing, session discovery, and the MCP surface. On its own it does nothing useful: with no editor running it exposes exactly one tool, which tells you no editor is running.
Related MCP server: unreal-engine-mcp
Why it is a separate process
Embedding an MCP server directly in the C++ plugin would be one program instead of two, which sounds simpler. It is not.
The MCP surface changes far more often than the engine bindings. Splitting them means the protocol layer can be rebuilt in seconds without recompiling a C++ module and restarting the editor.
The editor's game thread is precious. Everything touching a UObject must
run on it, and anything slow there freezes the editor. Keeping protocol,
framing, retries and transport outside means only the actual work is marshalled
onto that thread.
Crash isolation. A fault in protocol handling takes down a small external process, not an editor with unsaved work in it.
How it finds an editor
Nothing is configured. Each running editor advertises itself in a user-global registry:
%LOCALAPPDATA%/HullForge/sessions/<project>-<pid>.jsonEach entry holds a port, a per-session token, the project name and path, and a process id. The connector scans that directory, filters by whether the process is actually alive, and prefers the editor it is already connected to so a second editor opening does not silently move the target mid-conversation.
It declares the MCP listChanged capability and watches that registry, so tools
appear when an editor opens and disappear when it closes, without restarting
the client. That matters because MCP servers are launched by the client: a
connector that starts before the editor would otherwise report an empty tool
list forever, since the client has no reason to ask again.
One tool, hf_bridge_status, is implemented here rather than in the editor. It
is therefore always available, so "no tools" is never a silent state.
Reliability
Two things in here exist because the alternative loses work.
Idempotency. Every mutating call carries an operation_id. The connector
generates one per call and reuses it on transport retry, so a dropped connection
cannot apply the same change twice. The editor recognises a repeated id and
returns the original result.
Honest failure states. A call that definitely failed and a call whose outcome is unknown are different answers and are reported differently. "Unknown" means the connector stopped waiting, not that nothing happened, and the caller is told to verify before retrying.
Development
Requires Python 3.13 and uv.
uv sync
uv run pytest # unit tests, no editor needed
uv run pytest -m integration # needs a running editor with the pluginBuilding the distributable binary:
.\Build-Sidecar.ps1 # Nuitka, for release
.\Build-Sidecar.ps1 -Fast # PyInstaller, local iteration onlyBuild-Sidecar.ps1 explains why release builds use Nuitka rather than
PyInstaller, and re-runs a leak audit after every build rather than assuming the
result.
Installing
Most people should not build this. Install the packaged .mcpb bundle, which
contains a compiled binary and needs no Python.
In Claude Desktop: Settings > Extensions > Advanced settings > Extension Developer > Install Extension...
Double-clicking the .mcpb also works where the OS has an association
registered for it, but the menu above is reliable everywhere.
Full instructions: jigwright.com/hullforge/docs
Privacy
The connector collects nothing, transmits nothing, and contacts no server. All communication is over loopback. Full policy: jigwright.com/privacy.
Support
Documentation: https://jigwright.com/hullforge/docs
Issues in this repository, for the connector
Email support@jigwright.com for anything about the editor plugin
Licence
MIT, see LICENSE. This applies to the connector in this repository only. The HullForge editor plugin is a separate proprietary product under its own terms.
Available Tools
1 toolhf_bridge_statusBridge StatusARead-onlyIdempotent
Whether HullForge is connected to a running Unreal editor, and what to do if not. This tool is always available even when no editor is open. When an editor starts, the rest of the tools appear automatically - there is no need to restart the client.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral context beyond this: the tool is always available, and describes the automatic appearance of other tools when an editor starts. This explains the tool's behavior in the broader system workflow.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long and front-loaded with the core purpose. It is efficient and contains no filler. Could be slightly more concise by removing the second sentence about 'restart the client' if not essential, but overall it is well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description adequately covers what the tool does and its context in the toolset. It explains when it is used and how it relates to other tools. The only potential gap is not describing what the return value looks like, but since there is no output schema, the description still provides sufficient context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema already fully documents that. The description does not need to add parameter information since there are none. A score of 5 is appropriate as there is nothing missing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly indicates the tool checks connection status to a running Unreal editor and provides guidance if not connected. It specifies the verb ('Whether... connected') and the resource ('HullForge to Unreal editor bridge'), making the purpose clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool ('always available even when no editor is open') and what happens when an editor starts (other tools appear automatically). It implies the tool is for checking connection status and not for initiating connections, which is useful guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
hf_bridge_status
TDQS
With only a single tool, there is no possibility of overlapping purposes or confusion. The tool's purpose is clearly defined as a status check for the HullForge-Unreal connection.
The single tool name 'hf_bridge_status' follows a consistent snake_case convention and is descriptive of its function. There are no other tools to create inconsistency.
The server exposes only one tool for a connector that is expected to provide interaction with a running Unreal editor. The description hints at additional tools appearing dynamically, but the current set is extremely limited, making it a severe mismatch for the server's apparent scope.
The server's purpose is to bridge HullForge and Unreal Editor, yet the only tool available is a status check. There are no tools to perform any actual actions (e.g., launching assets, executing commands, or modifying editor state), leaving critical gaps that render the surface incomplete.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Cloud-hosted MCP server for durable AI memory
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceA two-process MCP bridge for Unreal Editor for Fortnite that lets Claude Code, Cursor, and other MCP clients drive a live UEFN editor safely.9-
- AlicenseBqualityCmaintenanceAn MCP server that gives AI agents broad control over Unreal Engine 5.7, enabling actor/asset/level management, Blueprint and material creation, screenshots, automation, and arbitrary editor Python execution.35MIT
- AlicenseNot gradedqualityAmaintenanceOpen-source MCP server connecting AI agents (Claude, Cursor, GitHub Copilot, Gemini, and more) to Unreal Engine 5.7, editor and runtime (C++ plugin + .NET sidecar).27Apache 2.0
- AlicenseBqualityAmaintenanceAn MCP server that lets an AI agent drive Unreal Engine 5: create projects, import assets, build levels and Blueprints, configure replication, compile C++, run Play In Editor and package the game.1004MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jigwright/hullforge-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server