MCP Image Server
MCP サーバー - 画像
URL、ローカルファイルパス、NumPy配列から画像を取得・処理するためのツールを提供する、モデルコンテキストプロトコル(MCP)サーバーです。このサーバーには、画像をMIMEタイプとともにBase64エンコードされた文字列として返すfetch_imagesというツールが含まれています。
私たちをサポートしてください
このプロジェクトが役に立ったと感じ、今後のプロジェクトを応援したいと思われた方は、ぜひコーヒーをご馳走ください!皆様のご支援は、革新的なAIソリューションの構築を支えていきます。
あなたの貢献は、インテリジェントでユーザーフレンドリーなアプリケーションを作成するという私たちの情熱を高めるのに大いに役立ちます。
Related MCP server: Image Toolkit MCP Server
目次
特徴
URL(http/https)から画像を取得する
ローカルファイルパスから画像を読み込む
大きなローカル画像に特化した処理
大きな画像(1MB以上)の自動画像圧縮
複数の画像の並列処理
異なるファイル拡張子に対する適切なMIMEタイプのマッピング
包括的なエラー処理とログ記録
前提条件
Python 3.10以上
uv パッケージ マネージャー (推奨)
インストール
このリポジトリをクローンする
uv を使用して仮想環境を作成し、アクティブ化します。
uv venv
# On Windows:
.venv\Scripts\activate
# On Unix/MacOS:
source .venv/bin/activateuv を使用して依存関係をインストールします。
uv pip install -r requirements.txtサーバーの実行
MCP サーバーを実行するには 2 つの方法があります。
1. 直接法
MCP サーバーを直接起動するには:
uv run python mcp_image.py2. ウィンドサーフィン/カーソルの設定
ウィンドサーフィン
この MCP サーバーを Windsurf に追加するには:
~/.codeium/windsurf/mcp_config.json にある設定ファイルを編集します。
次の構成を追加します。
{
"mcpServers": {
"image": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-image", "run", "mcp_image.py"]
}
}
}カーソル
この MCP サーバーをカーソルに追加するには:
カーソルを開いて設定に移動します(ナビゲーションバー→カーソル設定)
機能→ MCPサーバーへ移動
+ 新しいMCPサーバーを追加をクリックします
次の構成を入力します。
{
"mcpServers": {
"image": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-image", "run", "mcp_image.py"]
}
}
}利用可能なツール
サーバーは次のツールを提供します。
fetch_images : URL またはローカルファイルパスから画像を取得して処理します。パラメータ: image_sources: 画像への URL またはファイルパスのリスト。戻り値: base64 エンコードと MIME タイプを持つ処理済み画像のリスト。
使用例
次のようなコマンドを使用できるようになりました。
「これらの画像を取得: [URL またはファイル パスのリスト]」
「このローカルイメージを読み込んで処理します: [file_path]」
例
# URL-only test
[
"https://upload.wikimedia.org/wikipedia/commons/thumb/7/70/Chocolate_%28blue_background%29.jpg/400px-Chocolate_%28blue_background%29.jpg",
"https://imgs.search.brave.com/Sz7BdlhBoOmU4wZjnUkvgestdwmzOzrfc3GsiMr27Ik/rs:fit:860:0:0:0/g:ce/aHR0cHM6Ly9pbWdj/ZG4uc3RhYmxlZGlm/ZnVzaW9ud2ViLmNv/bS8yMDI0LzEwLzE4/LzJmOTY3NTViLTM0/YmQtNDczNi1iNDRh/LWJlMTVmNGM5MDBm/My5qcGc",
"https://shigacare.fukushi.shiga.jp/mumeixxx/img/main.png"
]
# Mixed URL and local file test
[
"https://upload.wikimedia.org/wikipedia/commons/thumb/7/70/Chocolate_%28blue_background%29.jpg/400px-Chocolate_%28blue_background%29.jpg",
"C:\\Users\\username\\Pictures\\image1.jpg",
"https://imgs.search.brave.com/Sz7BdlhBoOmU4wZjnUkvgestdwmzOzrfc3GsiMr27Ik/rs:fit:860:0:0:0/g:ce/aHR0cHM6Ly9pbWdj/ZG4uc3RhYmxlZGlm/ZnVzaW9ud2ViLmNv/bS8yMDI0LzEwLzE4/LzJmOTY3NTViLTM0/YmQtNDczNi1iNDRh/LWJlMTVmNGM5MDBm/My5qcGc",
"C:\\Users\\username\\Pictures\\image2.jpg"
]デバッグ
問題が発生した場合:
すべての依存関係が正しくインストールされていることを確認する
サーバーが実行中で接続を待機していることを確認します
ローカル画像の読み込みに関する問題については、ファイルパスが正しくアクセス可能であることを確認してください。
「サポートされていない画像タイプ」エラーの場合は、コンテンツタイプの処理を確認してください。
サーバー出力でエラーメッセージを探します
貢献
貢献を歓迎します!お気軽にプルリクエストを送信してください。
ライセンス
このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細についてはLICENSEファイルを参照してください。
Available Tools
1 toolfetch_imagesA
Fetch and process images from URLs or local file paths, returning them in a format suitable for LLMs.
This tool accepts a list of image sources which can be either:
1. URLs pointing to web-hosted images (http:// or https://)
2. Local file paths pointing to images stored on the local filesystem (e.g., "C:/images/photo1.jpg")
For a single image, provide a one-element list. The function will process images in parallel
when multiple sources are provided. Images that exceed the size limit (1MB) will be automatically
compressed while maintaining aspect ratio and reasonable quality.
Args:
image_sources: A list of image URLs or local file paths. For a single image, provide a one-element list.
Returns:
A list of Image objects or None values (if processing failed) in the same order as the input sources.
| Name | Required | Description | Default |
|---|---|---|---|
| image_sources | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and discloses key behavioral traits: parallel processing for multiple images, automatic compression for images over 1MB with aspect ratio and quality preservation, and failure handling (returns None for failed processing). It doesn't cover aspects like rate limits or authentication needs, but provides substantial 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 well-structured and front-loaded with the core purpose, followed by detailed input specifications, processing behavior, and return values. Every sentence adds value without redundancy, and it's appropriately sized for the tool's complexity.
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's moderate complexity (1 parameter, no output schema, no annotations), the description is largely complete: it covers purpose, input semantics, processing behavior, and return format. However, it lacks details on the 'Image objects' structure (e.g., format, metadata) and any error specifics, which would enhance completeness for an agent.
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 schema description coverage is 0%, so the description must compensate fully. It clearly explains the single parameter 'image_sources' as a list of URLs or file paths, specifies format examples (http/https URLs, local paths like 'C:/images/photo1.jpg'), and clarifies handling for single images (one-element list). This adds comprehensive meaning beyond the bare schema.
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 tool's purpose with specific verbs ('fetch and process images') and resources ('from URLs or local file paths'), and distinguishes its output format ('suitable for LLMs'). With no sibling tools, it fully defines its scope without redundancy.
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 implies usage by specifying input types (URLs or file paths) and handling of single vs. multiple images, but lacks explicit guidance on when to use this tool versus alternatives (e.g., other image tools or direct file handling). With no siblings, this is less critical but still a gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'fetch_images' has a clearly defined and distinct purpose that cannot be confused with any other tool in this server.
The single tool name 'fetch_images' follows a clear verb_noun pattern, and with only one tool, there is perfect consistency. No naming conventions can conflict when only one tool exists.
A single tool is generally too few for most server purposes, creating a thin surface that limits functionality. While this tool handles image fetching and processing well, the server's scope as an 'Image Server' suggests potential gaps that would require additional tools for comprehensive image operations.
For an 'Image Server' domain, having only a fetch/processing tool leaves significant gaps. There are no tools for image manipulation (resize, crop, filter), analysis (object detection, metadata extraction), or management (list, delete, organize images), making the surface severely incomplete for typical image-related workflows.
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 Model Context Protocol server for Wix AI tools
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseAqualityAmaintenanceModel Context Protocol server for fetching web content and processing images. This allows Claude Desktop (or any MCP client) to fetch web content and handle images appropriately.183640MIT
- AlicenseNot gradedqualityFmaintenanceA server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.18MIT
- AlicenseAqualityCmaintenanceA Model Context Protocol server that extracts images from URLs or base64 data and converts them into a format suitable for LLM analysis, allowing AI models to process and understand visual content.319721MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol server that enables Claude to display and interact with images from the local filesystem, allowing users to view images directly in conversations and retrieve image metadata.35
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/IA-Programming/mcp-images'
If you have feedback or need assistance with the MCP directory API, please join our Discord server