"Kit" matching MCP servers:

An opinionated brownfield planning workflow (PT-BR) with agents, slash-commands, and framework, shipped as an MCP server that syncs the kit into multiple IDE native layouts like Claude Code, Cursor, Codex, and others.

A provider-neutral MCP server that provides tools for managing skills, agents, references, and artifact memory in a local workspace.

Enables Codex to scaffold small framework-free websites and critique them with sourced, severity-annotated findings that teach better design and development choices.

Enables AI assistants and local workflows to run Jev-powered tools that judge speeches line by line, audit drafts against goals, bisect hard-to-test bugs, simulate common-sense physics, score note pairs, and ask arbitrary typed questions cheaply.

YouTube from an MCP server or the ytk CLI: search and read any public video, channel, playlist or comment, and manage your own channels: analytics, uploads, metadata, playlists and comment moderation.

Enables coding assistants to gather bounded source evidence, prepare typed judgments, and verify claims through MCP tools while leaving editing and execution to the host.

All-in-one 24-tool MCP runtime and 180-skill library providing protocol-level C4 workflow gates, cognitive reasoning engines, and safe execution for AI coding agents.

Enables automation of Xiaohongshu (Little Red Book) operations including content publishing, searching, and interacting, with MCP protocol support for AI agent integration.

Enables Codex to delegate tasks to ChatGPT through a browser-backed Oracle connection, with project memory and a verified-result cache. It supports preview, delegation, result polling, and explicit acceptance without an API fallback.

Integrates AI assistants with product management tools like Linear and Slack, providing specialized agents for discovery, strategy, prioritization, roadmap planning, and metrics definition via the Model Context Protocol.

Turn any website into a book you agent can read

Enables coding agents to run source-bound evidence checks and bounded batch judgments for classification, extraction, and decision tasks via TypeSafe Jev.

Lets any MCP-capable coding agent read and update an app's QA memory, test-case catalogs, coverage gaps, and Playwright run history. It exposes 11 tools covering status, scanning, case lookup, next-ID generation, memory search/add/forget, and result ingestion.

Enables grouping Conventional Commit subjects into Markdown release-note sections, including breaking changes, and scanning project files for TODO/FIXME/HACK/XXX comments with file:line while respecting project boundaries and result limits.

Enables driving Omniverse Kit apps (Isaac Sim, Isaac Lab) over MCP, allowing agents to control simulations, run Python, and call namespace-scoped tools via a single bridge.

Enables users to read and manage newsletter account data through the Kit API v4, covering subscribers, tags, broadcasts, sequences, snippets, statistics, and signed webhooks from natural-language MCP clients.

A starter kit for creating a read-only MCP server that lets AI assistants access business information, calculate prices, answer FAQs, and check availability.

An MCP server that generates MP4 b-roll videos from scene specs, enabling AI agents to create branded overlays for short-form video without After Effects.

A local, read-only MCP server that connects Claude to Monash University Moodle and Ed, providing access to deadlines, announcements, grades, lecture slides, course content, and Ed discussions.

A prompt-injection-aware MCP server demonstrating guardrails for agentic tool use, including permission tiers, untrusted-content quarantine, and heuristic injection detection, with a fictional ticket-triage assistant.