Browse the catalog

Self-healing DOM semantic selector resilient to class mutations (Tabbit / Stagehand)

AI outbound call simulator with structured field collection

Snowflake MCP provides a secure interface for querying Snowflake databases through external browser authentication, avoiding the need to store credentials on disk. It enables exploration of database schemas, tables, and views through a hierarchical resource structure, and includes a query tool for executing SQL statements with results limited to 1000 rows. The implementation emphasizes security by requiring users to manage permissions at the Snowflake account level, as it does not implement write restrictions within the MCP itself.

Open PRs, open issues, post comments, report check-run status, and open suggestion-style PRs (never direct commits) against GitHub repositories.

Enables AI hosts to call deterministic tools such as echo, add, reverse, read/write files, and a C++-implemented two_sum via the MCP stdio interface.

Provides access to as-built technical data of Chile's National Electric System (SEN) equipment, enabling query of installation types, companies, and detailed technical sheets with certification status via public API.

Quantifies R_V contraction signatures in AI models.

Cyclops MCP server provides AI assistants with safe Kubernetes application management through high-level abstractions, enabling creation and updates of applications using validated templates rather than direct manipulation of low-level Kubernetes resources. Built in Go using the cyclops-ui/cyclops framework, the implementation offers tools for managing Cyclops Modules (template-based application definitions), Template Stores (collections of Helm/Git/OCI templates), and retrieving JSON schemas for template validation, with comprehensive CRUD operations including module creation, updates, resource listing, and manifest generation. The server validates all module configurations against template schemas before deployment and integrates with Kubernetes through the Cyclops controller, serving DevOps teams who want to give AI agents controlled access to application deployment without risking direct cluster manipulation, and organizations seeking to abstract Kubernetes complexity from both developers and AI systems while maintaining production safety through template-driven workflows.

Redshift Query bridges AI assistants with Amazon Redshift data warehouses, allowing natural-language questions to be translated into read-only SQL queries executed via the Redshift Data API. It provides four tools for running queries, listing tables, describing schemas, and analyzing execution plans, with built-in row limits and timeout protection.

Community integration for the Mint Club V2 bonding curve token platform on Base blockchain. Provides tools for buying, selling, swapping, and creating tokens through AI agents.

Enables comprehensive control and automation of Yandex Browser, including tab management, content extraction, and console log monitoring. It supports element interaction, form filling, and JavaScript execution through the Model Context Protocol.

Enables sending emails through Gmail using your Gmail credentials. Provides a simple send_email tool that accepts recipient, subject, and plain text body parameters.

Provides tools to list, create, power on/off, and delete VMs on vCenter or ESXi hosts using natural language.

Enables AI agents to access Walmart product data including lookups, price history, offers, seller profiles, reviews, and sales stats via tools callable in MCP-compatible clients like Claude Desktop and Cursor.

MCP server that checks AI-generated CSS against design tokens, flagging off-brand values and suggesting the closest matching tokens for colors, spacing, radii, and typography.

Responsible & ESG investment portfolio analyzer (Portfolio Lab style)

Control smart home devices via Home Assistant API.

A Python package that enables LLM models to interact with Memos server through the Model Context Protocol interface, allowing search, creation, retrieval, and management of memos.

Parses USD/USDZ/USDA files into structured JSON for AI agents, enabling scene graph hierarchy, material shader graphs, spatial positions, and entity relationship analysis via CLI and MCP tools.

Provides a bridge to the traQ chat platform, enabling AI assistants to interact with traQ's messaging ecosystem through a set of standardized MCP tools. Supports retrieving information about channels, messages, users, stamps, and pins with flexible search and filtering capabilities. Built using Deno and the Model Context Protocol SDK, this implementation offers a clean, type-safe interface for querying traQ's API resources.