mcp-filter-adapter
Click on "Deploy 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., "@mcp-filter-adaptercapture the current viewport"
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.
mcp-filter-adapter
UE5 5.8 の MCP サーバーから、画面キャプチャなどの画像を取得できるようにするアダプタ
UE5 5.8 MCP の問題とツールの役割
CaptureViewport 等の Tool 利用時に、画像が text として返ってくるため AI が認識することが出来なくなっています。 またトークンを大量消費し、コンテキストウィンドウが溢れてツールが止まってしまう問題も発生します。
このツールは Client と UE5 MCP Server の間に入り、キャプチャ画像を正しく認識できる形に変換を行います。
Related MCP server: fm-mcp-comfyui-bridge
実際の動作
before(UE5 MCP サーバーの生レスポンス):
{ "content": [ { "type": "text",
"text": "{\"returnValue\":{\"image\":{\"mimeType\":\"image/png\",\"data\":\"iVBORw0KG...\"}}}" } ] }after(このアダプタ通過後):
{ "content": [
{ "type": "image", "mimeType": "image/png", "data": "iVBORw0KG..." },
{ "type": "text", "text": "{\"returnValue\": {\"image\": \"<image #0>\", \"cameraFOV\": 90, ...}}" } ] }使い方
既存の UE5 の mcp 設定を置き換えます。
元の UE5 MCP の設定
{
"mcpServers": {
"unreal-mcp": {
"type": "http",
"url": "http://127.0.0.1:8000/mcp",
]
}
}
}
↓ これを以下のように置き換える (<path>/mcp-filter-adapter の部分は clone したフォルダを指定)
{
"mcpServers": {
"unreal-mcp": {
"command": "uv",
"args": [
"run",
"--directory", "<path>/mcp-filter-adapter",
"mcp-filter-adapter",
"--upstream", "http://127.0.0.1:8000/mcp"
]
}
}
}uv をインストール
このリポジトリを git clone
mcp.json 等に上記エントリを追加
clone したフォルダを
--directoryで指定--upstreamには UE5 MCP Server の URL を指定
This server cannot be deployed
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Qwen Image 3 AI image generation
MCP server for Google Veo AI video generation
MCP server for Flux AI image generation
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for multi-provider AI image generation (AWS Bedrock, OpenAI, Google Gemini) enabling image generation, transformation, and editing through a unified interface.41MIT
- AlicenseAqualityDmaintenanceMCP server that provides image generation, captioning, and tagging via ComfyUI API, configurable for agent tools.43MIT
- AlicenseNot gradedqualityCmaintenanceLLM-native image optimization middleware & MCP server. Reduces vision model token consumption by preprocessing images into tile-boundary-aligned, padding-free formats.58 npm2Elastic 2.0
- AlicenseAqualityAmaintenanceMCP server that gives text-only AI agents the ability to understand images via vision tools, including multi-image analysis, OCR, comparison, and structured extraction. It uses providers like OpenAI, Anthropic, Gemini, and OpenRouter to return plain text descriptions.1010 npmMIT