欢迎使用pure.md的模型上下文协议 (MCP) 服务器。
pure.md让您的脚本、API、应用、代理等能够可靠地访问 Markdown 格式的 Web 内容——只需在任何 URL 前添加pure.md/即可。它可以避免机器人检测，并为 SPA 渲染 JavaScript，还能将 HTML、PDF、图像等转换为纯 Markdown 格式。就像 Markdown 内容的 CDN 一样，它会全局缓存对同一资源未来请求的响应，从而减轻源 Web 服务器的压力。
如果没有 puremd-mcp，本地代理可能无法获取网络内容。puremd -mcp 会教导 Cursor、Windsurf 和 Claude Desktop 等 MCP 客户端如何采用 pure.md 的功能，为它们提供网络解锁和搜索功能。
puremd-mcp 附带两个工具：
unblock-url - 从网页中提取 markdown 而不会被阻止
search-web - 在网络上搜索查询并将结果连接到 markdown 中
由 Anthropic 开发的模型上下文协议 (Model Context Protocol ) 是一项开放标准，使 AI 系统能够与工具生态系统无缝交互。借助该协议，Cursor、Windsurf 和 Claude Desktop 等 MCP 客户端可以学习如何使用各种 API 和其他功能。
生成 API 密钥是可选步骤，用于解锁更高的速率限制。如果您想匿名使用 pure.md MCP 服务器，只需将PUREMD_API_KEY值设置为空字符串 ( "" )。
在pure.md注册一个新帐户 — — 注册是免费的！
在仪表板中，生成一个新的 API 令牌
复制令牌，并将其用作 MCP 客户端配置文件中的PUREMD_API_KEY值（见下文）
Related MCP server: mult-fetch-mcp-server
将以下内容添加到您的~/.cursor/mcp.json文件：
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}将以下内容添加到您的./codeium/windsurf/model_config.json文件中：
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}将以下内容添加到您的~/Library/Application\ Support/Claude/claude_desktop_config.json文件中：
{
"mcpServers": {
"pure.md": {
"command": "npx",
"args": ["-y", "puremd-mcp"],
"env": {
"PUREMD_API_KEY": "<TOKEN>"
}
}
}
}要通过Smithery自动为 Claude Desktop 安装 puremd-mcp：
npx -y @smithery/cli install @puremd/puremd-mcp --client claude| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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.
search-webunblock-urlScored across 2 tools
The two tools have clearly distinct purposes: 'search-web' appears to perform web searches, while 'unblock-url' likely handles URL unblocking or access. There is no overlap in functionality, making them easily distinguishable.
Both tools follow a consistent verb-noun pattern with hyphen separation (e.g., 'search-web', 'unblock-url'), and they use clear, action-oriented verbs. There are no deviations in naming style.
With only 2 tools, the server feels thin and likely incomplete for a web-related domain. This minimal set suggests significant gaps in coverage, such as missing operations for browsing, filtering, or managing search results.
Inferred as a web search/access server, the toolset is severely incomplete. It lacks core operations like retrieving search results, handling pagination, or managing blocked URLs beyond unblocking. This will likely cause agent failures in typical workflows.
Turn any public website into an MCP server for agents to search, read and navigate.
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
