Skip to main content
Glama
enesjakozh
IA-Programming

MCP Image Server

by IA-Programming
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

MCP 服务器 - 图像

一个模型上下文协议 (MCP) 服务器，提供从 URL、本地文件路径和 NumPy 数组获取和处理图像的工具。该服务器包含一个名为 fetch_images 的工具，该工具会将图像以 base64 编码的字符串及其 MIME 类型返回。

支持我们

如果您觉得这个项目很有帮助，并且愿意支持未来的项目，不妨请我们喝杯咖啡！您的支持将帮助我们继续构建创新的人工智能解决方案。

您的贡献极大地激发了我们创建智能且用户友好的应用程序的热情。

Related MCP server: Image Toolkit MCP Server

目录

特征

  • 从 URL (http/https) 获取图像

  • 从本地文件路径加载图像

  • 专门处理大型本地图像

  • 大图像（>1MB）的自动图像压缩

  • 多幅图像的并行处理

  • 针对不同文件扩展名的正确 MIME 类型映射

  • 全面的错误处理和日志记录

先决条件

  • Python 3.10+

  • uv 包管理器（推荐）

安装

  1. 克隆此存储库

  2. 使用 uv 创建并激活虚拟环境：

uv venv
# On Windows:
.venv\Scripts\activate
# On Unix/MacOS:
source .venv/bin/activate

  1. 使用 uv 安装依赖项：

uv pip install -r requirements.txt

运行服务器

运行 MCP 服务器有两种方式：

1.直接法

直接启动 MCP 服务器：

uv run python mcp_image.py

2. 配置 Windsurf/Cursor

风帆冲浪

要将此 MCP 服务器添加到 Windsurf：

  1. 编辑配置文件 ~/.codeium/windsurf/mcp_config.json

  2. 添加以下配置：

{
  "mcpServers": {
    "image": {
      "command": "uv",
        "args": ["--directory", "/path/to/mcp-image", "run", "mcp_image.py"]
    }
  }
}

光标

要将此 MCP 服务器添加到 Cursor：

  1. 打开 Cursor 并进入设置（导航栏 → 光标设置）

  2. 导航至功能→ MCP 服务器

  3. 点击 + 添加新的 MCP 服务器

  4. 输入以下配置：

{
  "mcpServers": {
    "image": {
      "command": "uv",
      "args": ["--directory", "/path/to/mcp-image", "run", "mcp_image.py"]
    }
  }
}

可用工具

该服务器提供以下工具：

fetch_images ：从 URL 或本地文件路径获取并处理图像 参数：image_sources：图像的 URL 或文件路径列表 返回：已处理图像的列表，包含 base64 编码和 MIME 类型

使用示例

您现在可以使用以下命令：

  • “获取这些图片：[URL 或文件路径列表]”

  • “加载并处理此本地图像：[file_path]”

示例

# 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"
]

调试

如果您遇到任何问题：

  1. 检查所有依赖项是否正确安装

  2. 验证服务器正在运行并监听连接

  3. 对于本地图像加载问题，请确保文件路径正确且可访问

  4. 对于“不支持的图像类型”错误，请验证内容类型处理

  5. 查找服务器输出中的任何错误消息

贡献

欢迎贡献代码！欢迎提交 Pull 请求。

执照

该项目根据 MIT 许可证获得许可 - 有关详细信息，请参阅LICENSE文件。

Available Tools

1 tool
fetch_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.
ParametersJSON Schema
NameRequiredDescriptionDefault
image_sourcesYes

TDQS

A4.3/5.0
Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters5/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count2/5

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.

Completeness2/5

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

ActivityInactive
ResponsivenessNo issues

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

Related MCP Servers

Appeared in Searches

Latest Blog Posts

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