Browse the catalog

🤖👁️ 💻 Real-time SSH and shell session observer for Claude Code. Capture at the byte stream, advise without access.

An MCP server that enables the analysis of CSV and Parquet files by providing tools for statistical summaries, data previews, and structure exploration. It allows users to query local datasets and create sample data using natural language.

A server that enables LLMs to detect anomalies in sensor data by providing tools for data retrieval, analysis, visualization, and corrective action execution.

Enables LLMs to analyze and interact with Power BI (.pbix) files through PBIXRay capabilities. Provides access to data models, DAX measures, Power Query code, table relationships, and data contents with configurable tools and pagination support.

A hub server that connects to and manages other MCP servers, allowing users to bypass Cursor's 40-tool limit and reduce AI mistakes by hiding infrequently used tools.

Aviation agent toolkit: free MCP server + skills for CASA/FAA/EASA/ICAO regulations search. By Deepsky (The Compliance Team — audit automation for aviation operators).

This MCP server implementation provides a template for building custom MCP servers using TypeScript and the mcp-framework package. It sets up the basic project structure and configuration files needed to develop an MCP server, including TypeScript compilation settings and necessary dependencies. The implementation is designed as a starting point for developers looking to create their own MCP servers tailored to specific APIs or services.

Enables Claude to manage Todoist tasks and projects, including creating, listing, updating, completing tasks, and managing projects with natural language.

Agentic Kubernetes management with Strands agent and local Kubernetes MCP server.

Sentry-MCP-Server provides a bridge between AI assistants and Sentry error tracking platform, enabling retrieval and analysis of application errors through a standardized interface. The server exposes tools for fetching detailed issue information including stacktraces, error types, and occurrence statistics from Sentry projects. Built with TypeScript and the MCP framework, it authenticates with Sentry via API tokens, handles URL parsing for convenient issue referencing, and formats error data in a structured way. This implementation is particularly valuable for developers who need to investigate application crashes, monitor error trends, or troubleshoot production issues directly through conversational AI without context switching.

A MCP Server for TikTok videos that allows you to get video subtitles and post details, such as the number of likes, hashtags, and publishing time.

An MCP server that connects AI assistants to the NinjaOne remote monitoring and management platform via the REST API v2. It provides tools for device inventory, organization management, alert handling, maintenance scheduling, and automated job execution.

Provides the real exported API surface and type signatures of any npm package, extracted from its published TypeScript declarations, enabling AI coding agents to use functions accurately and avoid inventing nonexistent APIs.

E-commerce advertising policy scanner detecting prohibited claims and trademarks

A minimalist MCP server for interacting with Bauplan data tables and executing SQL queries against Iceberg tables stored in S3. It enables users to list tables, retrieve schemas, and run SELECT queries using standard MCP transports.

A thin MCP server that exposes Wolt's public consumer endpoints to AI agents, enabling discovery of nearby venues and fetching their menus with live prices and deal signals.

Connects to Deveras website quality scanners for accessibility auditing, AI search engine optimization analysis, and AI agent security verification. Provides tools to scan any URL for WCAG violations with severity-graded results, check AI engine optimization readiness, verify robots.txt and ai.txt compliance signals, estimate EU Accessibility Act compliance, and generate framework-specific code fix recipes for React, Vue, Angular, Svelte, and Next.js.

MCP server for linkfor.you — create and manage short links from Claude, Cursor, or any MCP client.

This MCP server provides AI assistants with feature flag management capabilities for Bucketeer, an open-source feature flag platform, built using TypeScript with the Model Context Protocol SDK and comprehensive error handling. The implementation offers five core tools for complete CRUD operations: listing feature flags with filtering and pagination support, creating new flags with configurable variations and targeting rules, retrieving specific flags by ID, updating existing flags with audit trail requirements, and archiving flags to make them inactive. Built with Zod schema validation, axios-based HTTP client with proper error mapping, and environment-based configuration supporting flexible deployment scenarios, it serves DevOps teams managing feature rollouts across multiple environments, product managers needing conversational access to feature flag controls, and development teams wanting to integrate feature flag operations into AI-assisted workflows without direct API interaction.