Code

Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

Gear — MCP server for Godot Engine with 110+ tools, compact/dynamic profiles, GDScript LSP, DAP debugger, screenshots, input injection, and CC0 asset search.

Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.

Selenium MCP server for AI agents — 39 browser automation tools with snapshots and sessions.

Generate MCP servers from natural language, OpenAPI specs, or database schemas.


An ability-resolution and governed execution layer for AI agents: use prepared providers first, then resolve abilities from the broader software world.

MCP server that delegates coding tasks to your locally installed pi CLI. Wraps the real binary instead of bundling its own copy of the agent, so it inherits your providers, models and extensions. Sessions survive restarts, calls are cancellable, and each

Model Context Protocol server for AWS Device Farm mobile automation via Appium

Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.

MCP server for real interactive terminal sessions — REPLs, SSH, databases, Docker

Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.

MCP server for generating diagrams, charts, presentations, and animations for Markdown documentation

Convention enforcement and AI code review for Claude Code — deterministic checks on every agent turn, AI review before every commit

Find vetted agent skills for your task, PyPI packages for your code, and research behind both — Skill Federation finder as a Node MCP server. Zero-install via npx; exposes find_skills / find_packages / find_research / get_skill_bundle tools to Claude and

Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.

FinishKit MCP: scan GitHub repos for security vulnerabilities, deployment blockers, and quality

Generate clinical SOAP notes, billing codes, and visit summaries from transcripts or audio.

Safety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in

Terminal AI agent with a native MCP client — automatic tool-calling, 5-layer security guardrails, optional Docker sandbox, and LangSmith observability. Powered by NVIDIA NIM.