Packages

AutoPentest is an agentic pentesting MCP server for web applications. It orchestrates multiple role-specialized agents (Scout/Analyzer/Exploiter/Reporter) across a structured multi-phase workflow that crawls and maps an application, then performs OWASP WSTG-aligned testing and PortSwigger technique-based exploitation attempts, producing evidence-backed reports and doing quality-gated verification. It also bundles security tooling in Docker and includes browser-based testing via a Playwright MCP component (per README).

Provides a local, read-only MCP server that exposes Bullhorn CRM data through a simple MCP tool interface by wrapping the CData JDBC Driver for Bullhorn CRM (SQL/relational model access via tools such as get_tables, get_columns, and run_query). Intended for LLM clients (e.g., Claude Desktop) to query live Bullhorn data without manually writing SQL.

Claude Code skill for detecting flaky test patterns that cause intermittent CI failures

VS Code extension that provides a unified interface for discovering, installing, and managing MCP servers and agent skills for GitHub Copilot, Claude Code, and Codex CLI. Includes a skills registry (skills.sh) and optional Cloud MCP remote deployment.

Provides a Model Context Protocol (MCP) server that exposes Docker Engine and Docker Swarm operations as MCP Tools, using the mcp_mediator framework to auto-generate tool interfaces from Docker client methods (optionally with @McpTool annotations).

[](https://github.com/vicentereig/dspy.rb)

json-server is a development tool that serves a full fake REST API from a local JSON file (or multiple files) by exposing typical CRUD endpoints for your data.

Provides an MCP (Model Context Protocol) server implemented with Spring Boot that authenticates to an ONES platform instance, fetches Wiki page content from a provided Wiki URL, converts the HTML to an AI-friendly Markdown/text representation, and returns structured page content (headings, paragraphs, lists, tables, images/links).

PAL MCP is a Python-based Model Context Protocol (MCP) server that provides a provider abstraction layer for orchestrating multiple AI model backends (e.g., Gemini, OpenAI, Anthropic, Azure, Grok, OpenRouter, local Ollama) and exposes multiple agentic “tools”/workflows (chat/thinkdeep/planner/consensus/codereview/precommit/debug, etc.). It also includes a CLI-to-CLI bridge tool (“clink”) to integrate external AI CLIs into workflows and to spawn isolated “subagents” within an existing CLI context.

Provides an MCP server (Python) that creates and edits PowerPoint (.pptx) presentations: generating deck files, adding different slide types (title, section header, title+content, tables, charts, pictures with captions), opening existing decks for editing, saving backups/final output, and optionally generating images via TogetherAI using a FLUX model.

Created by **[Anivar Aravind](https://anivar.net)**

reviewflow is an npm CLI/server that automates AI code reviews for GitHub PRs and GitLab merge requests. It receives webhook events, queues and deduplicates review jobs, runs multi-agent Claude Code reviews, reports structured progress via an MCP server, streams live status to a WebSocket dashboard, posts review results to the MR/PR, and performs follow-up reviews after fix pushes.

Provides a local MCP (Model Context Protocol) server for SAP HANA using CData JDBC Drivers. It is intended to expose SAP HANA data as callable MCP tools (table/column discovery and SQL SELECT execution) for local clients such as Claude Desktop, over stdio.

API Schema Drift Monitor — detect breaking changes in OpenAPI specs

spicebridge is an MCP server (and CLI) that lets an AI generate SPICE netlists and run ngspice simulations from natural-language/templated circuit descriptions. It supports AC/transient/DC analyses, measurement extraction, spec comparison, Monte Carlo/worst-case tolerance analysis, exporting (KiCad, schematic viewer), and optional cloud deployment via Cloudflare Tunnels.

Provides a read-only Model Context Protocol (MCP) server that exposes SQL Server Analysis Services data to MCP clients by wrapping the CData JDBC Driver for SQL Server Analysis Services. It supports listing tables/columns and executing SQL SELECT queries over the underlying SSAS data via MCP tools.

terminal-mcp (tmcp) is a minimal terminal CLI client for Model Context Protocol (MCP) servers. It can connect to MCP servers via stdio (local) or via streamable HTTP (remote), discover tools from configured servers, generate a tools.json allowlist, and let agents list and call only enabled tools via terminal commands.

Created by **[Anivar Aravind](https://anivar.net)**

Provides a local, read-only MCP server that wraps a CData JDBC Driver for Amazon Athena, exposing Athena tables/columns and SELECT query execution as MCP tools for AI clients (e.g., Claude Desktop).

Provides a local, read-only MCP server that exposes Bing Ads data (via CData JDBC Driver for Bing Ads) as MCP tools (list tables/columns and run SELECT queries). Intended to be used with MCP-capable desktop clients (e.g., Claude Desktop) through stdio on the same machine.