原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Driflyte MCP Server

作者:serkan-ozal版本 0.1.15i★ –i电脑或云端
注册名称com.driflyte/driflyte-mcp-server

安装

概览

作者提供的说明(英文原文)

Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

  • 在云端运行无需安装任何东西,通过互联网连接
  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://mcp.driflyte.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "driflyte": {
      "command": "npx",
      "args": [
        "-y",
        "@driflyte/mcp-server"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http driflyte https://mcp.driflyte.com/mcp

或者在你的电脑上运行

claude mcp add driflyte -- npx -y @driflyte/mcp-server

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "driflyte": {
      "url": "https://mcp.driflyte.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "driflyte": {
      "command": "npx",
      "args": [
        "-y",
        "@driflyte/mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "driflyte": {
      "type": "http",
      "url": "https://mcp.driflyte.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "driflyte": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@driflyte/mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://mcp.driflyte.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 driflyte.com 验证(注册中心会核实域名所有权)

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 7246 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7246 个服务器的 0% 更新
  • 基础检查结果等于或优于此分类中其他 7246 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Driflyte MCP Server 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.15)于13个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT今天更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Driflyte MCP Server

MCP Server for Driflyte.

The Driflyte MCP Server exposes tools that allow AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages. With this MCP server, Driflyte acts as a bridge between diverse, topic-aware content sources (web, GitHub, and more) and AI-powered reasoning, enabling richer, more accurate answers.

What It Does

  • Deep Web Crawling: Recursively follows links to crawl and index web pages.
  • GitHub Integration: Crawls repositories, issues, and discussions.
  • Extensible Resource Support: Future support planned for Slack, Microsoft Teams, Google Docs/Drive, Confluence, JIRA, Zendesk, Salesforce, and more.
  • Topic-Aware Indexing: Each document is tagged with one or more topics, enabling targeted, topic-specific retrieval.
  • Designed for RAG with RAG: The server itself is built with Retrieval-Augmented Generation (RAG) in mind, and it powers RAG workflows by providing assistants with high-quality, topic-specific documents as grounding context.
  • Designed for AI with AI: The system is not just for AI assistants — it is also designed and evolved using AI itself, making it an AI-native component for intelligent knowledge retrieval.

Usage & Limits

  • Free Access: Driflyte is currently free to use.
  • No Signup Required: You can start using it immediately — no registration or subscription needed.
  • Rate Limits: To ensure fair usage, requests are limited by IP:
  • `100` API requests per `5` minutes per IP address.
  • Future changes to usage policies and limits may be introduced as new features and resource integrations become available.

Prerequisites

  • Node.js 18+
  • An AI assistant (with MCP client) like Cursor, Claude (Desktop or Code), VS Code, Windsurf, etc ...

Configurations

CLI Arguments

Driflyte MCP server supports the following CLI arguments for configuration:

  • --transport - Configures the transport protocol (defaults to stdio).
  • --port – Configures the port number to listen on when using streamable-http transport (defaults to 3000).

Quick Start

This MCP server (using STDIO or Streamable HTTP transport) can be added to any MCP Client like VS Code, Claude, Cursor, Windsurf Github Copilot via the @driflyte/mcp-server NPM package.

ChatGPT
  • Navigate to Settings under your profile and enable Developer Mode under the Connectors option.
  • In the chat panel, click the + icon, and from the dropdown, select Developer Mode. You’ll see an option to add sources/connectors.
  • Enter the following MCP Server details and then click Create:
  • Name: Driflyte
  • MCP Server URL: https://mcp.driflyte.com/openai
  • Authentication: No authentication
  • Trust Setting: Check I trust this application

See How to set up a remote MCP server and connect it to ChatGPT deep research and MCP server tools now in ChatGPT – developer mode for more info.

Claude Code

Run the following command. See Claude Code MCP docs for more info.

Local Server
claude mcp add driflyte -- npx -y @driflye/mcp-server
Remote Server
claude mcp add --transport http driflyte https://mcp.driflyte.com/mcp
Claude Desktop
Local Server

Add the following configuration into the claude_desktop_config.json file. See the Claude Desktop MCP docs for more info.

{

"mcpServers": { "driflyte": { "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } }

Remote Server

Go to the Settings > Connectors > Add Custom Connector in the Claude Desktop and add the new MCP server with the following fields:

  • Name: Driflyte
  • Remote MCP server URL: https://mcp.driflyte.com/mcp
Copilot Coding Agent

Add the following configuration to the mcpServers section of your Copilot Coding Agent configuration through Repository > Settings > Copilot > Coding agent > MCP configuration. See the Copilot Coding Agent MCP docs for more info.

Local Server
{

"mcpServers": { "driflyte": { "type": "local", "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } }

Remote Server
{

"mcpServers": { "driflyte": { "type": "http", "url": "https://mcp.driflyte.com/mcp" } } }

Cursor

Add the following configuration into the ~/.cursor/mcp.json file (or .cursor/mcp.json in your project folder). Or setup by 🖱️One Click Installation. See the Cursor MCP docs for more info.

Local Server
{

"mcpServers": { "driflyte": { "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } }

Remote Server
{

"mcpServers": { "driflyte": { "url": "https://mcp.driflyte.com/mcp" } } }

Gemini CLI

Add the following configuration into the ~/.gemini/settings.json file. See the Gemini CLI MCP docs for more info.

Local Server
{

"mcpServers": { "driflyte": { "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } }

Remote Server
{

"mcpServers": { "driflyte": { "httpUrl": "https://mcp.driflyte.com/mcp" } } }

Smithery

Run the following command. You can find your Smithery API key here. See the Smithery CLI docs for more info.

npx -y @smithery/cli install @serkan-ozal/driflyte-mcp-server --client <SMITHERY-CLIENT-NAME> --key <SMITHERY-API-KEY>
VS Code

Add the following configuration into the .vscode/mcp.json file. Or setup by 🖱️One Click Installation. See the VS Code MCP docs for more info.

Local Server
{

"mcp": { "servers": { "driflyte": { "type": "stdio", "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } } }

Remote Server
{

"mcp": { "servers": { "driflyte": { "type": "http", "url": "https://mcp.driflyte.com/mcp" } } } }

Windsurf

Add the following configuration into the ~/.codeium/windsurf/mcp_config.json file. See the Windsurf MCP docs for more info.

Local Server
{

"mcpServers": { "driflyte": { "command": "npx", "args": ["-y", "@driflyte/mcp-server"] } } }

Remote Server
{

"mcpServers": { "driflyte": { "serverUrl": "https://mcp.driflyte.com/mcp" } } }

Components

Tools
  • list-topics: Returns a list of topics for which resources (web pages, etc ...) have been crawled and content is available. This allows AI assistants to discover the most relevant and up-to-date subject areas currently indexed by the crawler.
  • Input Schema: No input parameter supported.
  • Output Schema:
  • topics:
  • Optinal: false
  • Type: Array
  • Description: List of the supported topics.
  • search: Given a list of topics and a user question, this tool retrieves the top-K most relevant documents from the crawled content. It is designed to help AI assistants surface the most contextually appropriate and up-to-date information for a specific topic and query. This enables more informed and accurate responses based on real-world, topic-tagged web content.
  • Input Schema:
  • topics
  • Optinal: false
  • Type: Array
  • Description: A list of one or more topic identifiers to constrain the search space. Only documents tagged with at least one of these topics will be considered.
  • query
  • Optinal: false
  • Type: string
  • Description: The natural language query or question for which relevant information is being sought. This will be used to rank documents by semantic relevance.
  • topK
  • Optinal: true
  • Type: number
  • Default Value: 10
  • Min Value: 1
  • Max Value: 30
  • Description: The maximum number of relevant documents to return. Results are sorted by descending relevance score.
  • Output Schema:
  • documents:
  • Optional: false
  • Type: Array
  • Description: Matched documents to the search query.
  • Type: Document:
  • content
  • Optinal: false
  • Type: string
  • Description: Related content (full or partial) of the matched document.
  • metadata
  • Optinal: false
  • Type: Map
  • Description: Metadata of the document and related content in key-value format.
  • score
  • Optinal: false
  • Type: number
  • Min Value: 0
  • Max Value: 1
  • Description: Similarity score (between 0 and 1) for the content of the document.
Resources

N/A

Roadmap

  • Support more content types (.pdf, .ppt/.pptx, .doc/.docx, and many others applicable including audio and video file formats ...)
  • Integrate with more data sources (Slack, Teams, Google Docs/Drive, Confluence, JIRA, Zendesk, Salesforce, etc ...))
  • And more topics with their resources

Issues and Feedback

Please use GitHub Issues for any bug report, feature request and support.

Contribution

If you would like to contribute, please

  • Fork the repository on GitHub and clone your fork.
  • Create a branch for you

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx