Discover Awesome MCP Servers

engram-mcp

An MCP server that enables semantic and keyword search over Claude Code conversation history stored locally, using hybrid search, local embeddings, and time-decay scoring.

MCP Web Chat

A server that enables WebChat functionality through MCP (Model-Control-Protocol), solving long-term connection issues while providing both common method calls and business API integration capabilities.

rocket-cli

Rocket.Chat bridge with a local SQLite/FTS5 cache — CLI for humans, MCP server for LLM agents.

OpenFeature MCP Server

Provides OpenFeature SDK installation guidance for various programming languages and enables feature flag evaluation through the OpenFeature Remote Evaluation Protocol (OFREP). Supports multiple AI clients and can connect to any OFREP-compatible feature flag service.

天气 MCP 服务器

这是一个基于 FastMCP 构建的天气查询 MCP 服务器。 (This translates to: "This is a weather query MCP server built on FastMCP.")

SEO Performance MCP

A MCP server that turns your scattered SEO and analytics data into one clear verdict per URL. Plug it into Claude, Cursor, or any MCP-aware client and ask: "Which three posts should I update this week?" - and get an answer backed by hard numbers.

DevReview MCP Server

An AI-assisted code review tool that connects to a Supabase backend, enabling automated code review through MCP.

Sample Model Context Protocol Demos

好的，这是关于如何将模型上下文协议与 AWS 结合使用的一些示例： **总览** 模型上下文协议 (Model Context Protocol, MCP) 是一种标准化方法，用于将上下文信息传递给机器学习模型。这使得模型能够根据手头的任务更好地理解和响应。在 AWS 环境中，MCP 可以与各种服务集成，以增强模型的性能和可解释性。 **使用场景和示例** 以下是一些使用 MCP 与 AWS 结合的常见场景和示例： * **个性化推荐:** * **场景:** 构建一个推荐系统，根据用户的历史行为、人口统计信息和当前上下文（例如，一天中的时间、位置）来推荐产品或内容。 * **如何使用 MCP:** * 将用户历史行为、人口统计信息和上下文信息编码为 MCP 格式。 * 将 MCP 数据传递给您的推荐模型（例如，在 Amazon SageMaker 上部署的模型）。 * 模型使用 MCP 数据来生成个性化推荐。 * **AWS 服务:** Amazon Personalize, Amazon SageMaker, Amazon DynamoDB (存储用户数据), Amazon Location Service (获取位置信息) * **示例代码 (伪代码):** ```python # 假设我们已经从 DynamoDB 获取了用户数据，并从 Location Service 获取了位置信息 user_id = "user123" user_data = get_user_data_from_dynamodb(user_id) location_data = get_location_data_from_location_service(user_id) # 构建 MCP 数据 mcp_data = { "user_id": user_id, "user_history": user_data["purchase_history"], "user_age": user_data["age"], "location": location_data["city"], "time_of_day": "evening" } # 将 MCP 数据传递给 SageMaker 模型 response = sagemaker_endpoint.invoke(mcp_data) # 从响应中获取推荐结果 recommendations = response["recommendations"] ``` * **欺诈检测:** * **场景:** 检测金融交易中的欺诈行为，考虑交易金额、交易地点、用户行为模式等上下文信息。 * **如何使用 MCP:** * 将交易金额、交易地点、用户行为模式等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的欺诈检测模型。 * 模型使用 MCP 数据来评估交易的欺诈风险。 * **AWS 服务:** Amazon Fraud Detector, Amazon SageMaker, Amazon Kinesis (实时数据流), Amazon DynamoDB (存储用户行为数据) * **示例代码 (伪代码):** ```python # 假设我们已经从 Kinesis 获取了实时交易数据 transaction_data = get_transaction_data_from_kinesis() # 构建 MCP 数据 mcp_data = { "transaction_amount": transaction_data["amount"], "transaction_location": transaction_data["location"], "user_behavior": get_user_behavior_from_dynamodb(transaction_data["user_id"]) } # 将 MCP 数据传递给 Fraud Detector 或 SageMaker 模型 fraud_score = fraud_detector.detect_fraud(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 根据欺诈评分采取行动 if fraud_score > threshold: flag_transaction_as_fraudulent() ``` * **自然语言处理 (NLP):** * **场景:** 提高文本分类、情感分析或机器翻译等 NLP 任务的准确性，通过提供文档的上下文信息（例如，作者、来源、主题）。 * **如何使用 MCP:** * 将文档内容、作者、来源、主题等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的 NLP 模型。 * 模型使用 MCP 数据来更好地理解文本并提高性能。 * **AWS 服务:** Amazon Comprehend, Amazon SageMaker, Amazon S3 (存储文档), Amazon Kendra (企业搜索) * **示例代码 (伪代码):** ```python # 假设我们已经从 S3 获取了文档 document = get_document_from_s3("s3://my-bucket/my-document.txt") # 构建 MCP 数据 mcp_data = { "document_content": document, "document_author": "John Doe", "document_source": "News Article", "document_topic": "Politics" } # 将 MCP 数据传递给 Comprehend 或 SageMaker 模型 sentiment = comprehend.detect_sentiment(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 分析情感 print(f"Sentiment: {sentiment}") ``` * **图像识别:** * **场景:** 提高图像识别的准确性，通过提供图像的上下文信息（例如，拍摄地点、时间、天气）。 * **如何使用 MCP:** * 将图像数据、拍摄地点、时间、天气等信息编码为 MCP 格式。 * 将 MCP 数据传递给您的图像识别模型。 * 模型使用 MCP 数据来更好地识别图像中的对象。 * **AWS 服务:** Amazon Rekognition, Amazon SageMaker, Amazon S3 (存储图像), Amazon Location Service (获取位置信息) * **示例代码 (伪代码):** ```python # 假设我们已经从 S3 获取了图像 image = get_image_from_s3("s3://my-bucket/my-image.jpg") # 获取图像的元数据 (例如，通过 EXIF 数据) image_metadata = get_image_metadata(image) # 构建 MCP 数据 mcp_data = { "image_data": image, "location": image_metadata["location"], "time": image_metadata["time"], "weather": get_weather_data_from_location_service(image_metadata["location"]) } # 将 MCP 数据传递给 Rekognition 或 SageMaker 模型 objects = rekognition.detect_objects(mcp_data) # 或 sagemaker_endpoint.invoke(mcp_data) # 识别图像中的对象 print(f"Objects detected: {objects}") ``` **关键考虑因素:** * **数据格式:** 定义清晰的 MCP 数据格式，以便模型能够正确解析和使用上下文信息。 可以使用 JSON 或其他结构化数据格式。 * **数据量:** 考虑 MCP 数据的大小和复杂性，以及它对模型性能的影响。 优化数据传输和处理流程。 * **安全性:** 确保 MCP 数据的安全性，特别是当包含敏感信息时。 使用 AWS Identity and Access Management (IAM) 控制访问权限。 * **模型训练:** 在训练模型时，使用包含上下文信息的 MCP 数据，以便模型能够学习如何利用这些信息。 * **模型部署:** 确保模型部署环境能够接收和处理 MCP 数据。 可以使用 Amazon SageMaker Endpoints 或其他部署选项。 * **监控:** 监控模型的性能，并根据需要调整 MCP 数据或模型参数。 使用 Amazon CloudWatch 监控指标。 **总结:** 模型上下文协议 (MCP) 是一种强大的工具，可以提高机器学习模型的性能和可解释性。 通过将 MCP 与 AWS 服务集成，您可以构建更智能、更个性化的应用程序。 以上示例展示了 MCP 在不同场景下的应用，并提供了使用 AWS 服务的指导。 请根据您的具体需求进行调整和扩展。 希望这些示例对您有所帮助！ 如果您有任何其他问题，请随时提出。

COTI MCP Server

Enables AI applications to interact with the COTI blockchain for private token operations, supporting account management, private ERC20/ERC721 tokens, and secure transactions using Multi-Party Computation (MPC) technology.

aris-md/mcp

A minimal, well-structured MCP server implementation for learning and experimentation that exposes three tools: web search, API search, and client ID processing. It demonstrates clean separation between tool, transport, and LLM layers while supporting multiple AI clients through the Model Context Protocol standard.

PowerPoint MCP Server

A Model Context Protocol server that enables creating, editing, and manipulating PowerPoint presentations programmatically through Claude and other MCP-compatible clients.

Composio MCP Server

Exposes Composio tools and actions (Gmail, Linear, etc.) as MCP-compatible tools for language models to interact with in a structured way.

payroll-normalizer-mcp

Enables AI tools to normalize messy payroll spreadsheets (xlsx/xls/csv) into a standardized 10-column template for social insurance calculation, with automatic column detection, net-to-gross conversion, and cross-entity/month merging.

long-context-mcp

An MCP server implementing Recursive Language Models (RLM) to process arbitrarily large contexts through a programmatic probe, recurse, and synthesize loop. It enables LLMs to perform multi-step investigations and evidence-backed extraction across massive file sets without being limited by standard context windows.

PentestThinkingMCP

An AI-powered penetration testing reasoning engine that provides automated attack path planning, step-by-step guidance for CTFs/HTB challenges, and tool recommendations using Beam Search and MCTS algorithms.

Bitwig MCP Server

Bitwig Studio 的 MCP 服务器

mcp-stackexchange

Wraps the StackExchange API v2.3 to enable reading StackExchange data (questions, answers, etc.) without authentication. Allows AI agents to query StackExchange content through natural language or direct tool calls.

Directmedia MCP

Provides programmatic access to the Directmedia Publishing 'Digitale Bibliothek' collection, a 1990s German electronic book library containing 101 volumes of classic literature and philosophy with text extraction, search, and navigation capabilities.

mcp-skill-server

Build agent skills where you work — write a script, add a SKILL.md, and use it in Claude Code/codex/Cursor immediately. The same fixed entry point that runs locally deploys to production without a rewrite.

Paint MCP

Controls Windows Paint from Claude via GUI automation, enabling drawing of lines, rectangles, and freehand strokes on the canvas.

Cold Email Assistant

Automates cold email outreach for job applications by parsing job postings, generating personalized emails using AI, and sending them or saving as drafts in Gmail with resume attachments.

Semantica Search MCP

Semantic code search for Claude Code, enabling natural language codebase indexing and search using AI embeddings.

MCP Server Starter

A starter template for building MCP servers that enable AI assistants to interact with custom tools and data.

enoch-mcp

MCP server for the Enoch FastAPI control-plane API, enabling inspection and operation of an Enoch instance via tools.

guardrails-mcp-server

MCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.

TMDB MCP Server

A robust MCP server that wraps The Movie Database API, enabling LLMs to search movies, get details, popular movies, and recommendations.

ms-fabric-mcp-server

Enables AI agents to interact with Microsoft Fabric by exposing tools for managing workspaces, notebooks, SQL queries, pipelines, and Livy Spark sessions. It provides a comprehensive set of operations for data engineering and analytics tasks using standard Azure authentication.

Sentinel Signal MCP

MCP server for healthcare claims workflow scoring, validation, and feedback, supporting denial risk, prior authorization, and reimbursement assessment.

constraints-registry-mcp

A single, queryable source of engineering constraints that coding agents consult at code-generation time, exposed over an MCP server.

pyghidra-mcp

Exposes Ghidra reverse engineering capabilities via MCP, enabling LLMs and agents to analyze binaries, decompile, search, and edit programs headlessly or with GUI integration.