Browse the catalog

A Model Context Protocol server that analyzes YouTube videos, enabling users to extract transcripts, generate summaries, and query video content using Gemini AI.

AI orchestration for computational chemistry and HPC workflows.

Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do.

Book real estate showing tours from emailed or pasted listing details, including extracting listing data, preparing.

Provides Claude Desktop with custom tools for math, web search (DuckDuckGo), Wikipedia, ArXiv, and simulated Airbnb searches via MCP.

Complete personal finance management.

A template for deploying an unauthenticated MCP server on Cloudflare Workers. Enables rapid deployment of custom tools accessible from Claude Desktop and Cloudflare AI Playground without authentication requirements.

AI Runtime Meter gives developers a live token, cache & cost meter for Claude Code. Shows tokens, cache, model, source , cost and session totals per request. Run from any terminal or IDE.

Renders OHLCV data as candlestick chart PNGs and returns inline images. It is a pure renderer with no network access, allowing models to view charts generated from provided data.

Enables AI agents to safely decode and inspect JWT tokens and Base64 payloads in real-time.

Search grocery products, find store locations, add items to cart, and view profile across all Kroger-family stores.

Enables AI clients to access DTing business functions including company briefs, MCP tool suggestions, support replies, profile prompts, match context analysis, and safety checklists.

Actvt's embedded MCP server for macOS. 25 tools for live CPU, GPU, memory and network metrics, listening ports with a guarded port_kill, and Claude Code and Codex session analytics (cost, tokens, transcript search, error patterns). It ships inside the Actvt macOS app and binds to loopback on the user's machine, so it starts with the app, not as a standalone or containerised process.

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.