Skip to main content
Glama
enesjakozh
JeremyNixon

MCP Fetch

by JeremyNixon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

MCP 获取

铁匠徽章

用于获取 Web 内容和处理图像的模型上下文协议服务器。这使得 Claude Desktop（或任何 MCP 客户端）能够获取 Web 内容并进行适当的图像处理。

快速入门（针对用户）

要将此工具与 Claude Desktop 一起使用，只需将以下内容添加到您的 Claude Desktop 配置（ ~/Library/Application Support/Claude/claude_desktop_config.json ）中：

{
  "tools": {
    "fetch": {
      "command": "npx",
      "args": ["-y", "@kazuph/mcp-fetch"]
    }
  }
}

这将在需要时自动下载并运行该工具的最新版本。

所需设置

  1. 为 Claude 启用辅助功能：

    • 打开系统设置

    • 前往“隐私和安全”>“辅助功能”

    • 点击“+”按钮

    • 从您的应用程序文件夹添加 Claude

    • 为克劳德打开开关

自动剪贴板操作（Cmd+V）需要此辅助功能设置才能正常工作。

Related MCP server: @kazuph/mcp-fetch

对于开发人员

以下部分适用于那些想要开发或修改该工具的人。

先决条件

  • Node.js 18+

  • macOS（用于剪贴板操作）

  • Claude Desktop（从https://claude.ai/desktop安装）

  • tsx（通过npm install -g tsx ）

安装

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 MCP Fetch：

npx -y @smithery/cli install @kazuph/mcp-fetch --client claude

手动安装

git clone https://github.com/kazuph/mcp-fetch.git
cd mcp-fetch
npm install
npm run build

图像处理规格

处理来自 Web 内容的图像时，适用以下限制：

  • 每组最多 6 张图片

  • 每组最大高度8000像素

  • 每组最大为 30MB

如果内容超出这些限制，图像将自动分成多个组，并且您需要多次粘贴（Cmd+V）。

配置

  1. 确保 Claude Desktop 已安装并正在运行。

  2. 如果还没有安装 tsx，请全局安装：

npm install -g tsx
# or
pnpm add -g tsx

  1. 修改位于以下位置的 Claude Desktop 配置： ~/Library/Application Support/Claude/claude_desktop_config.json

您可以通过 Claude Desktop 菜单轻松找到它：

  1. 打开 Claude 桌面

  2. 在 Mac 菜单栏上单击 Claude

  3. 点击“设置”

  4. 点击“开发者”

将以下内容添加到您的 MCP 客户端的配置中：

{
  "tools": {
    "fetch": {
      "args": ["tsx", "/path/to/mcp-fetch/index.ts"]
    }
  }
}

可用工具

  • fetch ：从互联网检索 URL，并将其内容提取为 Markdown 文件。图像会自动处理并准备用于剪贴板操作。

笔记

  • 由于此工具依赖于 macOS 特定的剪贴板操作，因此仅适用于 macOS。

  • 使用 Sharp 处理图像以获得最佳性能和质量。

  • 当发现多幅图像时，它们会垂直合并，同时考虑尺寸限制。

  • 通过提取动画 GIF 的第一帧来自动处理动画 GIF。

Available Tools

1 tool
fetchA

Retrieves URLs from the Internet and extracts their content as markdown. If images are found, they are merged vertically (max 6 images per group, max height 8000px, max size 30MB per group) and copied to the clipboard of the user's host machine. You will need to paste (Cmd+V) to insert the images.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYes
maxLengthNo
startIndexNo
rawNo

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: content extraction to markdown, image merging with specific limits (max 6 images, max height 8000px, max size 30MB), and clipboard copying with a manual paste requirement. However, it omits details like error handling, rate limits, or authentication needs, leaving some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, starting with the core functionality. Every sentence adds value: the first covers retrieval and extraction, the second details image handling, and the third provides a usage note. It could be slightly more concise by integrating the image limits into one sentence, but overall it's efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (image processing, clipboard operations) and no annotations or output schema, the description is partially complete. It covers the main behaviors but lacks details on return values, error cases, or parameter effects. For a tool with 4 parameters and significant functionality, more context would be beneficial to fully guide an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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 for undocumented parameters. It mentions 'URLs' (plural) but only one 'url' parameter is required, and it does not explain the semantics of 'maxLength', 'startIndex', or 'raw'. The description adds no meaning beyond the schema, failing to address the coverage gap adequately.

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 ('retrieves URLs', 'extracts content as markdown') and resources ('URLs from the Internet'). It distinguishes itself by detailing the unique image handling behavior (merging, copying to clipboard), which is not implied by the name alone. No siblings exist to differentiate from, but the description is comprehensive.

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 for fetching and processing web content with images, but provides no explicit guidance on when to use this tool versus alternatives (e.g., other fetch tools or methods). It mentions a prerequisite ('You will need to paste...') but lacks context on exclusions or comparisons. With no sibling tools, this is adequate but not optimal.

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.

  1. 1 tool update
    • First observedfetch
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it to. The single tool 'fetch' has a clear and distinct purpose that cannot be confused with any other tool in this set.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tool names to compare it against. The name 'fetch' follows a simple verb pattern, which is appropriate for its function, and there is no inconsistency in naming conventions.

Tool Count2/5

A single tool is generally too few for most server purposes, as it limits functionality and may indicate an incomplete or overly narrow scope. For a server named 'MCP Fetch', which suggests fetching-related operations, having only one tool feels thin and insufficient for covering potential variations or related tasks in the domain.

Completeness2/5

The server's domain appears to be fetching and processing web content, but with only one tool, there are significant gaps in coverage. For example, there are no tools for handling different fetch methods, error handling, caching, or other related operations, which could lead to agent failures when more complex fetching scenarios arise.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches