Discover Awesome MCP Servers
Extend your agent with 16,348 capabilities via MCP servers.
- All16,348
- Developer Tools3,867
- Search1,714
- Research & Data1,557
- AI Integration Systems229
- Cloud Platforms219
- Data & App Analysis181
- Database Interaction177
- Remote Shell Execution165
- Browser Automation147
- Databases145
- Communication137
- AI Content Generation127
- OS Automation120
- Programming Docs Access109
- Content Fetching108
- Note Taking97
- File Systems96
- Version Control93
- Finance91
- Knowledge & Memory90
- Monitoring79
- Security71
- Image & Video Processing69
- Digital Note Management66
- AI Memory Systems62
- Advanced AI Reasoning59
- Git Management Tools58
- Cloud Storage51
- Entertainment & Media43
- Virtualization42
- Location Services35
- Web Automation & Stealth32
- Media Content Processing32
- Calendar Management26
- Ecommerce & Retail18
- Speech Processing18
- Customer Data Platforms16
- Travel & Transportation14
- Education & Learning Tools13
- Home Automation & IoT13
- Web Search Integration12
- Health & Wellness10
- Customer Support10
- Marketing9
- Games & Gamification8
- Google Cloud Integrations7
- Art & Culture4
- Language Translation3
- Legal & Compliance2
Watchtower DAP Windows Debugging
Enables step-through debugging for C#, Node.js/TypeScript, Python, and Dart applications on Windows through a unified MCP interface. Acts as a bridge between MCP clients and various debug adapters, providing consistent debugging workflows with breakpoints, variable inspection, and process attachment capabilities.
Web-QA
An AI-powered MCP server that automates web testing workflows by enabling recording, execution, and discovery of tests through natural language prompts.
Handwriting OCR
启用 MCP 客户端与手写 OCR 服务的集成,允许用户上传图像和 PDF 文档,检查处理状态,并以 Markdown 格式检索 OCR 结果。
Code Index MCP
ghas-mcp-server
镜子 (jìng zi)
PostgREST
这是一个用于 PostgREST 的 MCP 服务器。它允许 LLM 通过 PostgREST 对 Postgres 数据库执行数据库查询和操作。此服务器可与 Supabase 项目(使用 PostgREST)和独立的 PostgREST 服务器一起使用。
🧠 Model Context Protocol (MCP)
好的,这是使用 Langchain MCP Adapters 和 Ollama 实现 MCP 的演示: **标题:使用 Langchain MCP Adapters 和 Ollama 实现 MCP 的演示** **简介:** 本演示展示了如何使用 Langchain MCP Adapters 和 Ollama 来实现 MCP(多通道处理)。MCP 是一种技术,它允许您使用多个通道(例如,文本、图像、音频)来处理数据。这可以提高准确性和效率。 **先决条件:** * 已安装 Python 3.7 或更高版本 * 已安装 Langchain * 已安装 Ollama * 已安装 Langchain MCP Adapters **安装:** ```bash pip install langchain pip install ollama pip install langchain-mcp-adapters ``` **代码:** ```python from langchain_mcp_adapters import MultiChannelProcessor from langchain.llms import Ollama from langchain.chains import LLMChain from langchain.prompts import PromptTemplate # 1. 定义你的通道。 # 在这个例子中,我们将使用两个通道:文本和图像。 channels = [ { "name": "text", "type": "text", }, { "name": "image", "type": "image", }, ] # 2. 创建一个多通道处理器。 mcp = MultiChannelProcessor(channels=channels) # 3. 定义你的提示模板。 # 这个提示模板将用于处理文本通道。 text_prompt_template = """ 你是一个有用的助手。 请回答以下问题: {question} """ text_prompt = PromptTemplate( input_variables=["question"], template=text_prompt_template, ) # 4. 定义你的语言模型。 # 在这个例子中,我们将使用 Ollama。 llm = Ollama(model="llama2") # 5. 创建一个 LLM 链。 text_chain = LLMChain(llm=llm, prompt=text_prompt) # 6. 将 LLM 链添加到多通道处理器。 mcp.add_channel("text", text_chain) # 7. 定义一个函数来处理图像通道。 def image_processor(image_path): """ 这个函数将处理图像通道。 Args: image_path: 图像的路径。 Returns: 图像的描述。 """ # 在这里,你可以使用任何图像处理库来处理图像。 # 在这个例子中,我们将使用 PIL 库。 from PIL import Image import pytesseract # 打开图像。 image = Image.open(image_path) # 使用 pytesseract 来提取图像中的文本。 text = pytesseract.image_to_string(image) # 返回图像的描述。 return text # 8. 将图像处理器添加到多通道处理器。 mcp.add_channel("image", image_processor) # 9. 创建一个输入。 input_data = { "text": { "question": "什么是 Langchain?", }, "image": { "image_path": "image.png", }, } # 10. 处理输入。 output = mcp.process(input_data) # 11. 打印输出。 print(output) ``` **解释:** 1. **定义通道:** 首先,我们定义了两个通道:文本和图像。每个通道都有一个名称和一个类型。 2. **创建多通道处理器:** 接下来,我们创建了一个多通道处理器。多通道处理器负责处理来自不同通道的数据。 3. **定义提示模板:** 我们定义了一个提示模板,用于处理文本通道。提示模板是一个字符串,它包含一个或多个占位符。占位符将被输入数据替换。 4. **定义语言模型:** 我们定义了一个语言模型。语言模型是一个可以生成文本的模型。在这个例子中,我们使用 Ollama。 5. **创建 LLM 链:** 我们创建了一个 LLM 链。LLM 链是一个将提示模板和语言模型连接在一起的链。 6. **将 LLM 链添加到多通道处理器:** 我们将 LLM 链添加到多通道处理器。这告诉多通道处理器使用 LLM 链来处理文本通道。 7. **定义图像处理器:** 我们定义了一个图像处理器。图像处理器是一个可以处理图像的函数。 8. **将图像处理器添加到多通道处理器:** 我们将图像处理器添加到多通道处理器。这告诉多通道处理器使用图像处理器来处理图像通道。 9. **创建输入:** 我们创建了一个输入。输入是一个字典,它包含每个通道的数据。 10. **处理输入:** 我们处理输入。多通道处理器将使用 LLM 链和图像处理器来处理输入数据。 11. **打印输出:** 我们打印输出。输出是一个字典,它包含每个通道的处理结果。 **结论:** 本演示展示了如何使用 Langchain MCP Adapters 和 Ollama 来实现 MCP。MCP 是一种强大的技术,它可以提高准确性和效率。 **注意:** * 您需要将 `image.png` 替换为实际的图像文件。 * 您需要根据您的需要修改提示模板和图像处理器。 * 您可以使用任何语言模型来代替 Ollama。 希望这个演示对您有所帮助!
OmniMCP
一个服务器,它为人工智能模型提供丰富的用户界面上下文和交互能力,通过视觉分析和基于模型上下文协议的精确交互,实现对用户界面的深入理解。
My MCP server custom implementations
Feedback Collector MCP
Collects user feedback with text and image support through an Electron app, allowing AI tools to gather and process user input with customizable prompts and multiple response options.
Writer MCP
A Model Context Protocol server that manages character knowledge and relationships for creative writing projects, offering semantic search and AI-powered analysis.
Metabase MCP Server
Enables LLMs to interact with Metabase instances through 33 tools for querying cards, dashboards, databases, collections, and executing SQL queries against your Metabase installation.
Google Meet MCP Server
Google Meet MCP 服务器使 AI 代理能够创建、管理和检索 Google Meet 会议。它基于模型上下文协议构建,并公开了用于安排、更新和删除会议的工具,从而可以轻松集成 Google Meet 功能。
Tiny Chat
This is an LLM application with chat functionality, featuring chat using RAG, a database, and MCP server capabilities. The UI is designed for Japanese users.
Unichat
请发送使用 MCP 协议通过工具或预定义提示向 OpenAI、MistralAI、Anthropic、xAI 或 Google AI 发送请求。 需要供应商 API 密钥。
ExpressJS MCP
Exposes Express.js API endpoints as MCP tools, preserving existing schemas and authentication behavior. Supports streaming responses and can be mounted directly to existing Express apps or run as a standalone gateway.
AWS Nova Canvas MCP Server
一个 MCP 服务器,允许您使用 Amazon Bedrock 的 Nova Canvas 模型来生成和编辑图像,支持诸如文本到图像生成、图像修复(inpainting)、图像外延(outpainting)、图像变体和背景移除等功能。
Spurs Blog Mcp Server
一个为“Pounding The Rock”博客设立的MCP服务器,该博客提供对圣安东尼奥马刺队的全面报道。
SAP Business One MCP Server
Enables interaction with SAP Business One API through Azure Container Apps with VNet connectivity. Provides secure access to SAP data and operations through natural language interface.
MCP
For interacting with Algolia, "MCP servers" likely refers to **Management Console Protocol (MCP) servers**. However, Algolia doesn't directly use a concept called "MCP servers" in the traditional sense. Instead, Algolia provides several ways to manage and interact with your Algolia application, including: * **Algolia Dashboard:** This is the primary web-based interface for managing your Algolia application. You can configure indexes, manage API keys, view analytics, and perform other administrative tasks. * **Algolia API Clients:** These are libraries available in various programming languages (e.g., JavaScript, Python, PHP, Java, Ruby, Go, Swift, Kotlin) that allow you to programmatically interact with the Algolia API. These clients handle the communication with Algolia's servers. * **Algolia CLI (Command-Line Interface):** A command-line tool for managing your Algolia application from the terminal. * **Algolia Integrations:** Algolia integrates with various platforms and services, such as e-commerce platforms (e.g., Shopify, Magento), CMS systems (e.g., WordPress), and analytics tools. **Translation to Chinese:** The most accurate translation depends on the specific context. Here are a few options: * **If you want to emphasize the general concept of servers that manage Algolia:** * 用于与 Algolia 交互的 **管理服务器** (Yòng yú yǔ Algolia jiāohù de guǎnlǐ fúwùqì) - "Management servers for interacting with Algolia" * **If you want to be more specific and mention the Algolia API:** * 用于与 Algolia 交互的 **API 服务器** (Yòng yú yǔ Algolia jiāohù de API fúwùqì) - "API servers for interacting with Algolia" (This is more accurate as the API clients interact with Algolia's API servers) * **If you want to mention the Algolia Dashboard (which is a web-based interface):** * 用于与 Algolia 交互的 **管理控制台服务器** (Yòng yú yǔ Algolia jiāohù de guǎnlǐ kòngzhìtái fúwùqì) - "Management console servers for interacting with Algolia" (This is less common, as the dashboard is accessed through a web browser, not directly through a server connection) * **If you want to translate "MCP servers" literally, but with a note that it's not a standard Algolia term:** * 用于与 Algolia 交互的 **MCP 服务器** (Yòng yú yǔ Algolia jiāohù de MCP fúwùqì) - "MCP servers for interacting with Algolia" (Note: Algolia 本身不使用 "MCP 服务器" 这个术语 (Note: Algolia běnshēn bù shǐyòng "MCP fúwùqì" zhège shùyǔ) - Note: Algolia itself does not use the term "MCP servers") **Recommendation:** The best translation is likely **用于与 Algolia 交互的 API 服务器 (Yòng yú yǔ Algolia jiāohù de API fúwùqì)** because the Algolia API is the primary way to programmatically interact with Algolia's services. If you're referring to the web interface, then **用于与 Algolia 交互的 管理控制台服务器 (Yòng yú yǔ Algolia jiāohù de guǎnlǐ kòngzhìtái fúwùqì)** would be more appropriate, but less common. Avoid using "MCP servers" directly unless you're sure that's the intended terminology, and even then, include a clarifying note.
MCP Server for Asana
这个服务器实现允许 AI 助手与 Asana 的 API 交互,使用户能够通过自然语言请求来管理任务、项目、工作区和评论。
PDF2MD MCP Server
An MCP server that converts PDF files to Markdown format using AI sampling capabilities, supporting both local files and URLs with incremental conversion features.
Vercel MCP Adapter
Enables real-time communication between applications and AI models using the Model Context Protocol, supporting features like custom tools and multiple transport options for Next.js applications.
Google Drive server
用于与 Google Drive 集成的 Google Drive MCP 服务器,允许列出、读取和搜索文件。
ReactBits MCP Server
A Model Context Protocol server that provides AI assistants with access to ReactBits.dev components - a collection of 135+ animated React components for creative developers.
ClickUp Operator
一个与 Claude 兼容的 MCP 服务器,它通过一个简单的笔记存储系统和自定义 URI 方案,实现笔记的存储和总结功能。
Upcloud MCP Server
Yandex Tracker MCP Server
A Node.js MCP server that enables AI assistants to interact with Yandex Tracker task management system through a standardized protocol, supporting operations like creating, updating, and searching issues.
Next.js MCP Server
A Model Context Protocol server built with Next.js that provides AI assistants with access to custom tools and resources. Includes example tools for echoing messages and performing mathematical operations, with support for both SSE and HTTP transports.
MCP Wikidata Server
Provides access to Wikidata for Large Language Models through the Model Context Protocol, offering tools for entity search, detailed retrieval, SPARQL queries, relation exploration, and property-based searches.