Discover Awesome MCP Servers

YNAB MCP Server

An MCP server that provides Large Language Models with access to YNAB (You Need A Budget) budgets, allowing them to fetch budget data including accounts, categories, and category groups.

MCP SysOperator

A Model Context Protocol server enabling AI assistants to directly interact with infrastructure tools like Ansible and Terraform for executing playbooks, managing cloud resources, and performing other infrastructure operations.

vc-mcp

VidiCore 用 MCP サーバー

Archicad MCP Server

Enables MCP clients like Claude to interact with Graphisoft Archicad through the Tapir add-on's JSON commands. Supports automated Archicad operations and custom tool integration for architectural design workflows.

read-docs-mcp

A Model Context Protocol server that enables AI agents to access, search, and understand structured package documentation and source code from Git repositories. It automatically generates specialized tools to browse module overviews, components, and detailed documentation for technical libraries.

Snipe-IT MCP Server

Enables AI assistants to manage Snipe-IT inventory systems through comprehensive asset and consumable operations. Supports creating, updating, tracking, and managing IT assets, consumables, maintenance records, file attachments, and generating labels.

Jina AI MCP Server

Provides access to Jina AI's Search Foundation APIs for embeddings, web search, content extraction, reranking, classification, and semantic text segmentation.

MCP Prompt Template Selector

Provides AI-powered selection and generation of specialized system prompts from a database of over 66 templates for Claude Code. It uses semantic search to find the best matching template and can adapt it to fit specific user tasks and contexts.

Perplexity Server

I understand you're asking how to perform a web search using Perplexity AI's capabilities within an MCP (presumably referring to a specific environment or tool) without using API keys. Unfortunately, directly using Perplexity AI's search functionality *without* an API key is generally **not possible**. Perplexity, like most AI-powered search and language models, requires authentication (usually via an API key) to track usage, prevent abuse, and manage resources. Here's a breakdown of why and potential workarounds (though they won't be a direct replacement): * **Why API Keys are Necessary:** * **Authentication and Authorization:** API keys verify that you are a legitimate user and have permission to access the service. * **Usage Tracking:** Perplexity needs to track how much you're using their service to manage server load and potentially for billing (if it's a paid service). * **Rate Limiting:** API keys allow Perplexity to enforce rate limits, preventing any single user from overwhelming their servers. * **Security:** API keys help protect the service from unauthorized access and malicious activity. * **Possible Workarounds (with limitations):** 1. **Perplexity AI Website/App (If Allowed in your MCP):** The simplest approach is to use the Perplexity AI website or app directly, if your MCP environment allows external internet access and browser usage. You would manually enter your search queries and get the results. This doesn't require an API key because you're using their public interface. However, this isn't automated and doesn't integrate into your MCP workflow. 2. **Alternative Search Engines within MCP:** If your MCP has access to other search engines (e.g., Google, Bing, DuckDuckGo) *without* requiring API keys within that environment, you could use those. The quality of results and the AI-powered summarization won't be the same as Perplexity, but it's a possible alternative. You'd need to check the documentation of your MCP to see what search capabilities are built-in. 3. **Web Scraping (Highly Discouraged and Often Against Terms of Service):** Technically, you *could* try to scrape the Perplexity AI website. However, this is **strongly discouraged** for several reasons: * **Terms of Service Violation:** Web scraping is often against the terms of service of websites, including Perplexity AI. You could be blocked or face legal consequences. * **Fragility:** Website structures change frequently, so your scraping code would likely break often. * **Ethical Concerns:** Scraping puts a load on their servers and can be considered unethical if you're not respecting their resources. * **Complexity:** Bypassing anti-scraping measures can be very complex. 4. **Request an API Key (Recommended):** The best and most reliable solution is to request an API key from Perplexity AI. Even if it's a paid service, it's the proper way to use their API and ensures you're following their terms of service. Check their website for pricing and API key application details. 5. **Use a Different AI Model (If Allowed in your MCP):** If your MCP environment has access to other AI models that offer search or information retrieval capabilities (e.g., some open-source models), you could explore those. You'd need to research their capabilities and how to use them within your MCP. **In summary, while you can't directly use Perplexity AI's API without an API key, consider these alternatives, prioritizing ethical and compliant solutions. The best approach is to obtain an API key if you need to integrate Perplexity's search capabilities into your MCP.**

Eagle MCP Server

Eagle MCP Server

SpecLinter MCP

An AI-powered tool that transforms natural language specifications into structured, actionable development tasks with quality grading and Gherkin test scenarios. It also features semantic similarity detection to prevent duplicate work and validates implementations against original requirements.

Decision Tree MCP Server

Node.js で、.rtdq ファイルから決定木をロードして管理し、Redis をストレージとして使用して基本的な ToDo リスト機能を提供する MCP サーバー。

Perplexity MCP Server

Integrates with Perplexity's API to provide web search and AI-powered answers with citations. Offers a three-tier research workflow: search for sources, ask for grounded AI answers, and ask_more for deeper analysis using advanced models.

EdgeOne Pages MCP Server

Enables AI assistants to deploy and manage static websites directly through EdgeOne Pages. This self-hosted solution allows for direct file management and website hosting using EdgeOne's infrastructure and KV storage.

Confluence Knowledge Base MCP Server

Turns Confluence documentation into an AI-powered knowledge base, enabling natural language questions about your systems with answers retrieved from your actual documentation through semantic search.

OmniMCP

A semantic router that provides unified access to multiple MCP servers through a single tool interface, using vector search to discover and execute tools across your entire MCP ecosystem while minimizing context token usage.

X (Twitter) MCP server

X (Twitter) MCP server

Document Reading and Converter Tool

Enables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.

MCP Server for Quran.com API

鏡 (Kagami)

API-MARKET MCP Server

鏡 (Kagami)

ECharts MCP Server

A Model Context Protocol server that generates beautiful chart images from ECharts configurations, supporting various chart types with customizable dimensions.

MCP Fetch

Enables browser automation using Puppeteer through the MCP interface. Allows launching browsers, creating pages, and executing arbitrary JavaScript for web scraping, testing, and debugging tasks.

Sherlog MCP

Provides persistent IPython shell sessions per conversation with DataFrame-centric architecture, enabling stateful data analysis, CLI tool execution, and integration of external MCP servers within the same workspace context.

Coreflux MQTT MCP Server

Connects to a Coreflux MQTT broker and provides tools for managing Coreflux commands (models, actions, rules, routes) and executing MQTT operations through natural language interactions with AI assistants.

Taiwan Central Weather Administration MCP Server

台湾中央気象署 (CWA) API と連携するモデルコンテキストプロトコル (MCP) サーバー。

MCP SERVERLY

これは、モデルコンテキストプロトコル（MCP）の実装を、公式のAnthropic base SDK for dotnet 9で表現しようとするプロジェクトです。

MCP Web Utilities Server

Exposes tools for performing web searches via DuckDuckGo and fetching webpage content as simplified Markdown using crawl4ai. It enables language models to search the internet or specific websites and retrieve cleaned page text for analysis.

Dedalus MCP Documentation Server

Enables serving and querying documentation with AI capabilities, allowing users to search, ask questions, and get AI-powered answers from their documentation files. Built for seamless deployment on the Dedalus platform with OpenAI integration for enhanced document analysis.

Chuck Norris Jokes MCP Server

A simple MCP server that provides a tool called 'chistecitos' to fetch random Chuck Norris jokes from a public API.