Browse the catalog

Connect your AI assistant to Featuriq — the product feedback and roadmap tool for SaaS teams. Browse top feature requests, search feedback with natural language, update statuses, notify users when features ship, and manage your roadmap — all from your AI client. Authenticates via OAuth. No manual API key setup needed.

Provides zero-knowledge, local-first persistent memory for AI assistants with on-device embeddings, cross-platform capture, and zero-RTT semantic recall.

Enables RAG-based querying of local stock company data using a local LLM and vector database, providing tools to ask questions, search raw chunks, and list documents.

An MCP server that provides real-time weather alerts, forecasts, stock market data, and news information through various API integrations.

A CLI tool that sets up a Model Control Protocol server and deploys it to Cloudflare Workers, allowing you to quickly create custom tools for your Cursor Agent just by writing TypeScript functions.

Enables agents to identify appliances and retrieve grounded, robot-executable operation packages, reducing hallucinations from 24% to nearly 0%.

亚马逊跨境电商场景下的 Claude / AI Agent Skills 合集（中文优先，聚焦 Amazon 出海 + 1688 供货上游）

MCP server for reading, writing, and rendering Scapple (.scap) files

Lets AI assistants read, command, and debug microcontrollers over a serial connection via MCP. Provides tools for serial port discovery, reading serial output, sending commands, and decoding register values.

Coda MCP Server acts as a bridge between AI assistants and the Coda API, allowing interaction with Coda documents through a standardized interface. Built with TypeScript and the Model Context Protocol SDK, it provides tools for listing, creating, reading, updating, and duplicating pages within a specified Coda document. The server communicates over standard input/output, requires a Coda API key and document ID for authentication, and can be easily added to AI assistants like Cursor or Claude Desktop through a simple npx command. It's particularly useful for collaborative document management, content creation, and knowledge base maintenance directly from AI assistant conversations.

Provides access to Google Search Console to retrieve and analyze search performance data including queries, pages, and rankings. It enables users to perform rich data analysis through customizable reporting periods and dimensions using the Search Console API.

A remote MCP server deployed on Cloudflare Workers with OAuth, enabling tools like math operations and integration with Claude Desktop via SSE.

Evaluates websites for crawling compliance and safety by analyzing robots.txt files, detecting anti-crawling mechanisms, identifying sensitive data, checking copyright restrictions, and scanning for exposed endpoints to provide three-tier risk ratings with specific recommendations for compliant web scraping strategies.

Sample MCP server using Typescript

This MCP server implementation provides a bridge to Data.gov, enabling AI assistants to interact with government datasets. Developed by Joao Bondan, it offers tools for searching packages, retrieving dataset details, listing groups and tags, and accessing specific resources. The server is designed to facilitate data-driven analysis and research using public government information, making it valuable for projects requiring access to official U.S. datasets.

Provides access to VisiData functionality for data analysis, visualization, and transformation across multiple formats. Supports advanced features like correlation heatmaps, skills analysis, salary benchmarking, and statistical distribution plots.

Deploys Microsoft's Playwright MCP server to Render, providing a public MCP URL for streamable HTTP or SSE connections. Enables browser automation and interaction via natural language in clients like Cursor, Cline, Claude, and VS Code.

Bridges your Nightscout CGM data with AI assistants via the Model Context Protocol, enabling natural language queries about glucose readings, treatments, statistics, and pattern analysis.

Env-conditioned stack-trace retrieval for agent debugging over MCP, enabling search for known fixes, contribution of new solutions, and feedback-driven ranking.

MCP server for Contextium — pipe team SOPs, coding standards, agents, skills, and workflows directly into Claude, Cursor, and other AI coding assistants.