3,944 skills. One install layer.

Expose Convex functions as MCP tools with zero boilerplate

Autopilot workflow — autonomous task execution with reasoning, context management, and shell commands.

MCP server with built-in tools across multiple domains for AI-assisted JavaScript analysis and security analysis — browser automation, CDP debugging, network monitoring, JS hooks, code analysis, and workflow orchestration

Batch execution patterns — run multiple operations sequentially, in parallel, or as a pipeline.

Minimal MCP server over stdio with typed tools and rich content helpers

MCP daemon for cross-agent collaboration

FaberJS MCP server — AI coding agent integration for Claude Code, Cursor, and Claude Desktop

TypeScript types and JSON Schema for MCP server specifications. Define, validate, and share static snapshots of Model Context Protocol servers.

A Model Context Protocol (MCP) server that provides access to the Metropolitan Museum of Art Collection through natural language interactions. This server allows AI models to search The Met's art collection and have art works available as a Resource.

MCP (Model Context Protocol) server for leakferret. Stops AI agents from committing live secrets.

MCP server for TAPD (Tencent Agile Product Development) - manage stories, tasks, bugs, iterations, and more via AI assistants

MCP server for Atlassian Confluence and Jira Cloud APIs

Full project audit workflow — code quality review, security scan, architecture analysis, and metrics report.

Agent registry — register AI agents with capabilities, list available agents, query capabilities.

Browser SDK for Tesseron. Declares actions and resources, opens a WebSocket to the local gateway.

Session metrics tracking — token usage, costs, duration, and per-tool statistics.

Persistent key-value memory — store and recall information across sessions as JSON files.

Knowledge base — index documents, search by content, fetch entries, purge stale data, rank by relevance.

OpenCodeHub — SARIF v2.1.0 helpers (merge + enrich)

Agent Model Layer — One-line LLM access with built-in memory. 29 providers, 18 embeddings, zero lock-in.

Centrali MCP Server - AI assistant integration for Centrali workspaces

Change impact analysis — given a file or symbol, find what files are affected by a change.

MCP server middleware for atrib. Signed receipts for every tool call, one-line integration.

MCP server for managing git worktrees with synchronized branches. Provides tools for creating isolated development environments, tracking changes, and managing collaborative workflows.