mcp_server

Pedagogical word enrichment for AI agents. One API call returns what would cost 5 separate calls + an LLM generation: definition, IPA pronunciation, etymology as narrative, a teaching insight from Kelly (AI tutor), translations in 8 languages with native pronunciations, 3 age-appropriate explanations (kid/adult/senior), and a knowledge graph of connected words. Pre-computed and edge-cached on Cloudflare D1 — ~3ms response globally. Also includes 62,000 daily lesson segments across 365 days, 11 languages, and 3 age tiers. Built for tutoring agents, language learning apps, and educational chatbots. 6 tools: word_enrich, word_translate, word_connections, word_search, word_batch, lesson_of_day.

Provide your AI agents with "eyes." This server enables open-vocabulary object detection and instance segmentation using naturally phrased text prompts (e.g., "detect the laptop next to the coffee").

百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

Summarize and search coding sessions, automatically extract rules from session discoveries (dead ends, decisions, gotchas) and benchmark performance across coding agents. Works with Claude Code, Codex CLI and Cursor.

Retrieving and analyzing issues from Sentry.io

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

VaultSage MCP lets your AI agent store, search, and chat over persistent cloud files. No local install—sign in with Google, copy one token, and connect via a single MCP URL to use file search, uploads, directory browsing, and share links from Cursor or Claude Desktop.

Query maritime vessel tracking data via natural language. Search vessels by name/IMO/MMSI, get real-time positions, ETAs, portevents, emissions, inspections, casualty records, and NAVTEX safety messages. Powered by vesselapi.com.

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

AI agent access to Obsidian vault through MCP protocol. Read, search, and write notes via Team Relay collaborative server. Supports shared folders, real-time sync, and full-text search. Works with Claude Code, Codex CLI, OpenCode, and any MCP-compatible client. Install: uvx evc-team-relay-mcp PyPI: https://pypi.org/project/evc-team-relay-mcp/ GitHub: https://github.com/entire-vc/evc-team-relay-mcp

IndieStack plugs into your AI editor. Before it writes code, it checks if a free indie tool already does it.

Save notes semantically, don't simply save them

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Stop letting AI hallucinations eat your hours. With this engine, your work flows smoothly while a full SRE squad of models codes and debugs on your behalf. Are you building complex applications, only to find that AI hallucinations are eating your entire afternoon? You know the loop: You ask Claude or Cursor to fix a bug. It gives you a snippet. It breaks something else. You paste the error back. It forgets the original architecture and responds with "// ... rest of your code here". What started as a 5-minute feature turns into a 3-hour circular debugging nightmare. If this engine actually works, you are saved. The Qwen Engineering Engine (powered by the Lachman Protocol) completely stops the "two steps forward, one step back" dance. Instead of relying on a single, forgetful LLM to do everything, this MCP Server deploys a dedicated, specialized squad of Qwen models to your local codebase: - Zero Placeholders: The dedicated qwen_coder tool writes 100% complete, production-grade files. No lazy snipping. - Deep Debugging: Instead of pasting logs to Claude, the qwen_audit tool unleashes QwQ (Qwen's reasoning model) to act as your Senior Auditor. It reads the files, finds the memory leak, and tells you exactly what failed. - Architectural Immunity: Before writing code, the qwen_architect drafts a JSON roadmap and self-verifies it against your stack. If it's a bad idea, it rejects it *before* breaking your app. Why Qwen? Because running an entire squad of GPT-4o or Claude 3.5 Opus models to constantly rewrite files would cost you $50 a day. By routing this heavy lifting through Alibaba's DashScope API (Qwen 3.5 Plus & Qwen 2.5 Coder 32B), the cost is literal fractions of a cent. Let your main assistant (Claude/Antigravity/Cursor) be the Commander. Let the Qwen Engine do the heavy lifting in the trenches. Stop chatting. Start shipping.

Trust-and-knowledge MCP server for agent ecosystems: score trust, verify/certify agents, register identities, and query a Neo4j-backed knowledge graph.

A Serper MCP Server

The QA Prompts MCP Server is a Model Context Protocol (MCP) server designed specifically for mobile automation teams. It provides structured, reusable QA prompt templates that can be used directly inside Cursor to streamline automation development, debugging, and bug reporting. It integrates with Cursor through MCP, allowing teams to trigger predefined QA workflows using simple slash commands in chat. What It Does This MCP server offers ready-to-use prompts for: Converting manual test cases into automation code Reviewing and refactoring automation frameworks Analyzing test failures Standardizing bug reports Generating Page Object Model (POM) locators from Appium Inspector XML All outputs are structured and formatted to match professional QA standards and framework conventions. How to Use It in Cursor (No Repository Clone Required) You don’t need to clone the repository to use it. Simply add the server configuration to your Cursor MCP configuration file located at: ~/.cursor/mcp.json Add this configuration: Use npx Point to the GitHub repository: swapnilGirishPawar/Custom-MCP-Server-Mobile-QA After saving the configuration, restart Cursor. The QA prompts will then appear in chat when you type /. Available Prompts 1. Manual to Automation Conversion These prompts help automation engineers generate or improve test code: /convert-manual-to-automation Converts manual test cases into complete Appium + Java + TestNG automation scripts following Page Object Model (POM) architecture. /refactor-automation-code Performs a detailed PR-style review of automation code and returns a structured improvement report. /xml-to-pom-locators Converts Appium Inspector page source XML into properly prioritized POM locator declarations (ID → Accessibility ID → XPath). 2. Debugging & Failure Analysis /analyze-test-failure Analyzes Appium failure logs to determine: Root cause Severity Flakiness risk Fix recommendations This helps teams quickly understand why a test failed and how to resolve it. 3. Bug Standardization /standardize-bug-report Converts a simple bug description into a fully structured bug report using a standardized organization template. This ensures consistent, professional bug documentation. How the Workflow Looks in Cursor Open Cursor chat (Cmd+L) or Composer (Cmd+I) Type / Select one of the available QA prompts Fill in the required inputs Submit The AI processes the structured template and returns formatted, production-ready output. Example Workflows Standardizing a Bug You type: /standardize-bug-report Provide: bugDescription: “login button not working on iOS after update” additionalContext (optional): Build 2.3.1, iPhone 15, Premium account The system generates: Proper bug title Detailed issue description Reproduction steps Expected result Structured formatting Converting a Manual Test Case to Automation You type: /convert-manual-to-automation Provide: featureNavigation (e.g., Settings → Notifications → Push Notifications) manualTestCase (your test steps) existingCode (optional Page Objects or BaseTest) The system generates: Complete TestNG test class Proper annotations POM-based implementation Framework-aligned structure Prompt Input Requirements Each prompt requires specific inputs: convert-manual-to-automation Required: featureNavigation, manualTestCase Optional: existingCode refactor-automation-code Required: code xml-to-pom-locators Required: pageSourceXml analyze-test-failure Required: failureLogs standardize-bug-report Required: bugDescription Optional: additionalContext Local Development Setup If you want to modify or extend the MCP server: Clone the GitHub repository Install dependencies using npm Build the project Start it locally For development with auto-reload, use the dev script (requires tsx). To test locally before pushing changes, you can point your Cursor MCP configuration to your local build output (dist/index.js) instead of the GitHub source. Tech Stack The server is built using: TypeScript (strict mode enabled) @modelcontextprotocol/sdk (v1.27+) Zod v4 for input validation stdio transport for integration with Cursor Summary The QA Prompts MCP Server acts as a structured QA assistant embedded inside Cursor. It eliminates repetitive prompt writing and standardizes automation generation, debugging, and bug documentation workflows. It’s particularly useful for: Mobile automation engineers QA leads Teams using Appium + Java + TestNG Organizations aiming for consistent bug reporting standards

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

MCP server that gives AI agents real crypto trading capabilities. 13 tools across market data, order execution, grid strategies, and Cardano DeFi. Connects to Bitget, Gate.io, MEXC, and Kraken. Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client. Open-source, MIT-licensed.

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

25 read-only tools for searching, analyzing, and exploring your entire iMessage history on macOS. Spotify Wrapped for texts, conversation analytics, streaks, reactions, read receipts, and more. Everything runs locally.

Generate hyper-personalized cold email sequences. List campaigns, generate emails for individual leads or batches, and export results as CSV or JSON.

Your ML & AI Knowledge Wiki. Learnt by AI, built by AI, for AI. Expert-level knowledge across the full ML & AI stack, from fine-tuning and distributed training, to inference serving and GPU kernel optimization, to building agents and RAG pipelines. 1000+ frameworks and libraries, all in one place. This MCP server turns your AI coding agent (Claude Code, Cursor, OpenAI Codex, ...) into an ML/AI expert engineer. Browse the full knowledge base at leeroopedia.com.

Flag features directly from chat in your code editor, including VS Code, Cursor, Windsurf, Claude Code—any IDE with MCP support.