通过远程 Python 执行与虚幻引擎实例交互的服务器实现。
🚀虚幻实例管理
通过多播自动发现虚幻节点
实时节点状态监控
通过 LSP 兼容客户端列出资源
💻远程执行
在虚幻引擎环境中执行 Python 代码
支持有人值守和无人值守的执行模式
文件执行和语句评估模式
📊日志记录和监控
详细记录到文件（ mcp_unreal.log ）
具有不同详细程度的控制台日志记录
节点连接健康监控
Related MCP server: unreal-mcp
# Clone repository
git clone https://github.com/your-org/mcp-unreal-server.git
cd mcp-unreal-server
# Install dependencies
pip install -r requirements.txt在RemoteExecutionConfig中配置多播参数：
# Default multicast settings (modify in server.py)
config.multicast_group_endpoint = ("239.0.0.1", 6766)修改server.py中的日志配置：
# Adjust log levels
file_handler.setLevel(logging.DEBUG) # File logging
console_handler.setLevel(logging.INFO) # Console loggingpython -m src.mcp_server_unreal.server连接到虚幻实例
{
"host": "239.0.0.1",
"port": 6766
}执行 Python 代码
{
"node_id": "<unreal-node-id>",
"code": "print('Hello Unreal')",
"unattended": true
}types.Resource(
uri="unreal://<node_id>",
name=f"Unreal Instance: {node_id}",
description="Unreal Engine instance",
mimeType="application/x-unreal"
)模式 | 描述 |
模式执行文件 | 执行 Python 文件 |
模式执行语句 | 执行 Python 语句 |
模式评估语句 | 计算 Python 表达式 |
常见问题：
未发现节点：验证虚幻实例是否正在使用 MCP 插件运行
执行超时：检查防火墙设置中的多播流量
连接断开：监视mcp_unreal.log以了解节点状态变化
Apache-2.0许可证
在Unreal中执行Python代码
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| unattended | No |
| Name | Required | Description |
|---|---|---|
| error | No | |
| result | No | |
| success | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't describe important behavioral aspects: whether this executes synchronously or asynchronously, what permissions are required, how errors are handled, whether it's safe for production use, or what the 'unattended' parameter actually means behaviorally. The description is minimal and lacks critical operational context.
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 extremely concise - a single phrase that directly states the core function. There's zero wasted language, and it's perfectly front-loaded with the essential information. For its length, it's maximally efficient, though this conciseness comes at the cost of completeness.
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 that this is a code execution tool with no annotations, 2 parameters (one with unclear purpose), and an output schema exists, the description is insufficient. While the output schema may describe return values, the description doesn't address safety concerns, execution context, error handling, or parameter meanings. For a potentially powerful/dangerous operation like code execution, more context is needed.
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?
Schema description coverage is 0%, so the description must compensate but doesn't. It mentions no parameters at all, leaving both 'code' and 'unattended' completely unexplained. The description doesn't clarify what format the Python code should be in, what execution environment is used, or what 'unattended' mode entails. This is inadequate for a tool with 2 parameters and 0% schema coverage.
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 states the action ('执行Python代码' - execute Python code) and the context ('在Unreal中' - in Unreal). It specifies both verb and resource, though it doesn't need to distinguish from siblings since none exist. The purpose is unambiguous but could be more specific about what kind of Python execution this enables.
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?
No guidance is provided about when to use this tool versus alternatives. The description doesn't mention prerequisites, limitations, or typical use cases. With no sibling tools, differentiation isn't needed, but basic usage context would help the agent understand appropriate scenarios for this operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0execute-pythonScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear, distinct purpose of executing Python code within Unreal.
With only one tool, naming consistency is inherently perfect. The tool name 'execute-python' follows a clear verb_noun pattern, and there are no other tools to create inconsistency.
A single tool is too few for a server named 'MCP Unreal Server', which suggests a broader scope related to Unreal Engine. This minimal toolset feels thin and inadequate for typical Unreal automation or interaction tasks.
The tool surface is severely incomplete for an Unreal server. It only provides Python execution, lacking essential operations like asset management, level editing, blueprint interaction, or any other common Unreal Engine workflows, leaving significant gaps.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Control Unreal Engine to browse assets, import content, and manage levels and sequences. Automate…
Hosted MCP server for task-first delegation to remote workstations and workers.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.