发现优秀的 MCP 服务器

instant-mcp

A local mock MCP server for building against the Model Context Protocol. Write a tool in the browser, save it, and it is immediately available on an MCP endpoint.

screenshot-vision-mcp

An MCP server that captures screenshots of URLs or local app windows and analyzes them with a local Ollama vision model, enabling Claude to visually inspect web pages and desktop applications without sending image data externally.

India Market MCP

Comprehensive MCP server for Indian stock market with 60 tools covering NSE/BSE, derivatives, mutual funds, technicals, and more, requiring no API keys. Enables users to access live market data, analyze indicators, and manage investments through natural language.

Kynth Core MCP

Enables document parsing, field extraction, PII redaction, contract analysis, chargeback handling, and company enrichment via the Kynth Core API. Provides tools for Claude and any MCP client to process documents and extract structured data.

israel-weather-mcp

MCP server that uses Playwright to scrape real-time weather forecasts for Israeli cities and returns structured text data (temperature, humidity, wind) to LLMs.

mcp_odoo_fresh

Enables AI agents to interact with Odoo ERP to perform sales tasks such as searching clients and products, and creating and confirming quotations via the MCP protocol.

entroly-context-engine

Entroly is a high-performance context engineering engine that optimizes AI coding agent context windows through information-theoretic compression and reinforcement learning. It gives your AI 100% codebase visibility while reducing token consumption by an average of 78%.It's learns fully autonomously.

consensa-mcp

An MCP server that records consented, attributed, paid-for receipts for open-source dependencies, settling per-call USDC payments on Algorand with on-chain attribution.

Storyblok MCP

Enables to manage Storyblok components through natural language descriptions, including creating and updating components with various field types.

Blackwell Bank Card Hub MCP

Enables users to explore and manage banking card features including product discovery, comparison, eligibility checks, spend insights, merchant offers, travel notices, card controls, and digital wallet provisioning.

tuiml

TuiML is an agent-native ML runtime that lets you install, connect to your AI agent, and run real ML workflows—classification, regression, clustering, experiments—from one structured interface.

queue-inspector-mcp

An MCP server that lets an agent inspect and operate Redis-backed job queues, supporting Asynq and BullMQ backends with per-state counts, job details, and state transitions.

baomihua-formatter

A Node.js MCP server for inspecting and operating on media files in OpenList and CloudDrive2, plus querying TMDB movie and TV metadata.

parseapi-mcp

Official parseAPI MCP server providing IP/place data, email/phone/domain validation, weather, currency, timezone, and holiday lookups as tools for AI agents.

local_ai_gen

Local AI generation for images, audio, speech, and 3D models using open source models.

fortnox-mcp-server

Enables AI agents to manage invoices, customers, suppliers, accounting entries, orders, and more through Fortnox's cloud accounting platform via natural language.

mcp-server-mssql

Provides tools to connect, query, and manage Microsoft SQL Server databases through the MCP protocol, including support for stored procedures, transactions, and schema inspection.

Scrapbox Cosense MCP Server

这个服务器方便与 cosense/Scrapbox 项目进行交互，使用户能够检索、列出、搜索和创建页面，同时支持各种查询操作并安全访问私有项目。

shopify-multistore-mcp

Enables conversational Admin API read/write across multiple Shopify stores with a production write-gate for safety.

kagi-session2api-mcp

Provides free web search and URL summarization using Kagi session tokens, compatible with any MCP client.

Webpage MCP Server

Enables querying and retrieving webpage content from websites by parsing sitemap.xml files and fetching HTML content from specified URLs. Includes built-in rate limiting for responsible web scraping.

Vision MCP Server

Provides image understanding capabilities for MCP clients (e.g., Claude Code) by analyzing images using vision models from providers like Alibaba Cloud Bailian, OpenAI, or OpenRouter, returning detailed descriptions in Markdown format.

synology-office-mcp

Self-hosted MCP server that exposes Synology Drive, Spreadsheet, MailPlus, and Calendar as structured tools for AI agents, enabling file, spreadsheet, email, and calendar management via natural language.

Petstore MCP Server

A read-only MCP server that exposes Swagger Petstore v2 GET endpoints as tools for searching available pets, fetching pet details, and checking inventory.

crest-verify

Verify x402 endpoints before your agent spends. Three tools: verify (SPEND/CAUTION/INVESTIGATE/DO NOT SPEND backed by 50K+ services), passport (full trust identity), risk_check (deep assessment). No API keys, no signup.

Postman MCP Generator

Generates MCP servers from Postman API requests, automatically creating JavaScript tools that enable LLMs to interact with any API documented in Postman collections. Supports authentication configuration and deployment via STDIO or SSE.

YouTube Crawler MCP Server

Enables YouTube data crawling and AI-powered summarization of videos, including channel metadata retrieval, time-range queries, and automatic transcription with multi-language support.

coin-mcp-server

Okay, here's a breakdown of how to use Bitget's API to get cryptocurrency information, along with considerations and a basic example. I'll provide both the English explanation and the Chinese translation. **English Explanation** **1. Understanding the Bitget API:** * **REST API:** Bitget primarily uses a RESTful API. This means you'll be making HTTP requests (GET, POST, etc.) to specific URLs (endpoints) to retrieve data or perform actions. * **Authentication:** Some endpoints (especially those dealing with your account or trading) require authentication. This involves using API keys (a public key and a secret key) that you generate on the Bitget platform. Keep your secret key *very* safe. * **Rate Limits:** Bitget, like most exchanges, has rate limits. This restricts the number of requests you can make within a certain time period. Exceeding these limits will result in your requests being temporarily blocked. Check the Bitget API documentation for the specific rate limits. * **Documentation:** The *most important* resource is the official Bitget API documentation. Find it on the Bitget website (usually under "API" or "Developer" sections). The documentation will list all available endpoints, required parameters, response formats, and authentication details. **Always refer to the official documentation first.** **2. Basic Steps:** 1. **Get API Keys (if needed):** If you need to access private data (like your account balance or place orders), create API keys on the Bitget website. Enable the necessary permissions (e.g., "Read," "Trade"). 2. **Choose an Endpoint:** Decide what information you want. Examples: * **Market Data:** Get the current price of Bitcoin (BTC), trading volume, order book, etc. * **Account Information:** Get your account balance, order history, etc. (requires authentication). * **Trading:** Place buy/sell orders (requires authentication). 3. **Construct the Request:** Build the HTTP request to the correct endpoint, including any required parameters. This often involves creating a URL with query parameters. 4. **Send the Request:** Use a programming language (Python, JavaScript, etc.) and an HTTP client library (e.g., `requests` in Python, `axios` in JavaScript) to send the request to the Bitget API. 5. **Parse the Response:** The Bitget API will return a response, usually in JSON format. Parse the JSON to extract the data you need. 6. **Handle Errors:** Check the HTTP status code and the response body for any errors. Implement error handling in your code. **3. Example (Python using `requests` - Market Data - Public Endpoint):** ```python import requests import json # Replace with the actual Bitget API endpoint for ticker information (e.g., BTCUSDT) api_url = "https://api.bitget.com/api/spot/v1/ticker/BTCUSDT_SPBL" #Example endpoint, check documentation try: response = requests.get(api_url) response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx) data = response.json() print(json.dumps(data, indent=4)) # Pretty print the JSON # Example: Extract the last price last_price = data['data']['close'] print(f"Last price of BTCUSDT: {last_price}") except requests.exceptions.RequestException as e: print(f"Error: {e}") except (KeyError, TypeError) as e: print(f"Error parsing JSON: {e}") ``` **Important Notes:** * **Security:** Never hardcode your secret API key directly into your code. Use environment variables or a secure configuration file. * **Error Handling:** Implement robust error handling to catch network errors, API errors, and JSON parsing errors. * **API Versioning:** Bitget may update its API. Pay attention to the API version in the endpoint URL (e.g., `/api/v1/`, `/api/v2/`) and update your code accordingly when necessary. * **Testing:** Thoroughly test your code in a test environment (if Bitget provides one) before using it with real funds. * **Legal:** Be aware of any legal or regulatory requirements related to using cryptocurrency exchange APIs in your jurisdiction. **Chinese Translation** **1. 理解 Bitget API:** * **REST API:** Bitget 主要使用 RESTful API。 这意味着您将向特定的 URL（端点）发出 HTTP 请求（GET、POST 等）以检索数据或执行操作。 * **身份验证:** 某些端点（尤其是处理您的帐户或交易的端点）需要身份验证。 这涉及使用您在 Bitget 平台上生成的 API 密钥（公钥和私钥）。 请 *非常* 安全地保管您的私钥。 * **速率限制:** 像大多数交易所一样，Bitget 具有速率限制。 这限制了您在特定时间段内可以发出的请求数量。 超过这些限制将导致您的请求被暂时阻止。 请查看 Bitget API 文档以获取具体的速率限制。 * **文档:** *最重要* 的资源是官方 Bitget API 文档。 在 Bitget 网站上找到它（通常在“API”或“开发者”部分下）。 该文档将列出所有可用的端点、必需的参数、响应格式和身份验证详细信息。 **始终首先参考官方文档。** **2. 基本步骤:** 1. **获取 API 密钥（如果需要）：** 如果您需要访问私有数据（例如您的帐户余额或下订单），请在 Bitget 网站上创建 API 密钥。 启用必要的权限（例如，“读取”、“交易”）。 2. **选择一个端点:** 确定您想要的信息。 例子： * **市场数据:** 获取比特币 (BTC) 的当前价格、交易量、订单簿等。 * **帐户信息:** 获取您的帐户余额、订单历史记录等（需要身份验证）。 * **交易:** 下买入/卖出订单（需要身份验证）。 3. **构建请求:** 构建到正确端点的 HTTP 请求，包括任何必需的参数。 这通常涉及创建带有查询参数的 URL。 4. **发送请求:** 使用编程语言（Python、JavaScript 等）和 HTTP 客户端库（例如 Python 中的 `requests`，JavaScript 中的 `axios`）将请求发送到 Bitget API。 5. **解析响应:** Bitget API 将返回一个响应，通常为 JSON 格式。 解析 JSON 以提取您需要的数据。 6. **处理错误:** 检查 HTTP 状态代码和响应正文是否有任何错误。 在您的代码中实现错误处理。 **3. 示例（Python 使用 `requests` - 市场数据 - 公共端点）：** ```python import requests import json # 替换为实际的 Bitget API 端点以获取行情信息（例如，BTCUSDT） api_url = "https://api.bitget.com/api/spot/v1/ticker/BTCUSDT_SPBL" #示例端点，请查阅文档 try: response = requests.get(api_url) response.raise_for_status() # 为错误的状态代码（4xx 或 5xx）引发异常 data = response.json() print(json.dumps(data, indent=4)) # 漂亮地打印 JSON # 示例：提取最新价格 last_price = data['data']['close'] print(f"BTCUSDT 的最新价格：{last_price}") except requests.exceptions.RequestException as e: print(f"错误：{e}") except (KeyError, TypeError) as e: print(f"解析 JSON 时出错：{e}") ``` **重要提示:** * **安全:** 永远不要将您的秘密 API 密钥直接硬编码到您的代码中。 使用环境变量或安全配置文件。 * **错误处理:** 实现强大的错误处理以捕获网络错误、API 错误和 JSON 解析错误。 * **API 版本控制:** Bitget 可能会更新其 API。 注意端点 URL 中的 API 版本（例如，`/api/v1/`、`/api/v2/`），并在必要时相应地更新您的代码。 * **测试:** 在将您的代码用于真实资金之前，请在测试环境中彻底测试您的代码（如果 Bitget 提供）。 * **法律:** 请注意您所在司法管辖区与使用加密货币交易所 API 相关的任何法律或监管要求。 **Key Takeaways:** * **Read the Documentation:** The Bitget API documentation is your bible. * **Start Simple:** Begin with public endpoints (no authentication required) to get familiar with the API. * **Handle Errors:** Robust error handling is crucial. * **Security First:** Protect your API keys. I hope this comprehensive explanation and example are helpful! Remember to consult the official Bitget API documentation for the most up-to-date information. Good luck!

Casper Agentic Portfolio Copilot

AI-driven portfolio dashboard and MCP server for the Casper blockchain, enabling wallet monitoring, validator staking analysis, RWA compliance checks, and on-chain transaction generation.

FinanceMarker MCP Server

MCP server for integrating FinanceMarker.ru with LLM agents, IDEs, n8n, and other MCP-compatible clients. It proxies the FinanceMarker REST API and exposes it as a set of MCP tools.