3,627 skills. One install layer.

Track and report token savings — compare FocusMCP usage vs naive full-read, trend over time, ROI.

Local-first agent memory MCP — cross-agent brain with drift detection, 6-layer structured memory + token-saving file diff cache

Electron.js MCP server — IPC scaffolding, security auditing, build tooling, and development intelligence for AI assistants

A Model Context Protocol (MCP) server that acts as a passthrough proxy with hook middleware support

Reconstruct CLI — auth, MCP install (Cursor, Claude Code, Copilot, Codex), and bundled assistant plugins

Symbol lookup in source files — find, get, bulk, body.

NEUS makes trust portable across the internet — so people, apps, and AI agents can prove what is real before access, payout, or execution.

MCP server for AI coding agents - process management, reverse proxy with traffic logging, browser instrumentation, and sketch mode

agentry MCP server — the canonical entry point. Drop it into Claude Code, Cursor or any MCP-compatible AI and your assistant can read your app's errors, analytics and deploys directly.

AGLedger MCP Server — Thin API pass-through for AI agents via MCP protocol

React hooks adapter for Tesseron. useTesseronAction, useTesseronResource.

MCP server for Munition x402-paid agent services

MCP server for Carbonstop Agent internal skill APIs

MCP server for Estonian e-arveldaja (e-Financials) API

MCP server for running GitHub Actions workflows locally

Semantic search using TF-IDF vector space — cosine similarity, intent matching, document similarity.

Task management for multi-agent workflows — create tasks, assign to agents, track status, mark complete.

TypeScript SDK for mpak registry - MCPB bundles and Agent Skills

Security-hardened MCP server for Excalidraw with API key auth, rate limiting, and real-time canvas sync

Standalone MCP server for Copass — drop-in discover/search/get_origin + Context Window tools for any MCP client (Claude Agent SDK, Claude Code, Claude Desktop, Cursor)

Persistent SSH PTY session manager for MCP clients with actor-aware input tracking, terminal-style dashboard rendering, and automatic session cleanup.

CLI for MCP Mesh — build distributed AI agents with auto-discovery, dependency injection, and LLM integration

Parallel execution coordination — run tasks concurrently, collect results, merge outputs, handle timeouts.

Pay-per-tool-call gating proxy for MCP servers. Wrap any MCP server with API key auth, per-tool pricing, rate limiting, and usage metering.