Open-Source ListingsOpen-Source

Prompt Shield

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

Mycelium

🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

AgentHound

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability graph and detects reachable attack paths from untrusted input to sensitive data or external action, with live control simulation.

Book Writing AI Agent

An intelligent, multi-agent system to autonomously plan, write, edit, fact-check, and publish a complete book using the CrewAI framework and Groq's LLaMA-3-70B model. This AI pipeline mimics the collaborative process of human authors, editors, and publishers to streamline creative book development.

MCP Servers Schemas

This document provides a list of different MCP servers. For each server, we provide a schema definition that includes the latest basic information and tool definitions.

Windbg MCP

MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --listen

Libre Office MCP

A cross-platform LibreOffice MCP server for AI assistants. Create, read, edit, and automate Writer documents, Calc spreadsheets, and Impress presentations.

Mcpflo

A visual testing tool for MCP (Model Context Protocol) servers — connect, browse capabilities, and inspect tools, resources, and prompts. Think Bruno, but for MCP.

Mockloop MCP

Intelligent Model Context Protocol (MCP) server for AI-assisted API development. Generate mock servers from OpenAPI specs with advanced logging, performance analytics, and server discovery. Optimized for AI development workflows with comprehensive testing insights and automated analysis.

Browser Agent

Replayable Browser Agent

Comics Now

The modern, self-hosted comic book library server, smart reader, and AI-augmented cataloging platform

Agent Airlock

A type-checker and contract layer for AI agent tool calls: in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

AI Garage

Mini-Projects using Cutting-Edge AI Frameworks

Typed Evals

Fast, typed Python framework for Jev-as-a-Judge/Decision-model evaluation for LLMs, RAG, and AI agents along with human-label calibration.

Cowork To Code Bridge

Let Claude run code on your real machine — safely — from any Claude chat. Bridges Claude Cowork to Claude Code on your Mac/Linux box. One command, idempotent, no open ports.

Rest To MCP Adapter

A Python library for converting REST API specifications into MCP (Model Context Protocol) tools for AI agents.

Wildberries MCP

MCP server for Wildberries — marketplace orders, analytics, stock (Russia). Part of WWmcp — 46 MCP servers for emerging markets.

Octoweb

Keyboard-first AI browser for macOS — WebKit + Rust, built-in AI sidebar, isolated workspaces, and an MCP server that lets your agents drive the web.

Azure Devops MCP Onprem

MCP server for on-premises Azure DevOps Server (TFS) with TFVC support - shelvesets, changesets, Work Items, Git, Pipelines, Test Plans, Wiki for AI assistants.

Platform

The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-demo

MCP Box

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.

Summoner Core

Summoner's core SDK for building and deploying agents

GenAI GCP HF OpenAI Databricks

GenAI - Building AI Workflows | Agentic Appls | Working with LLMs | HuggingFace | OpenAI | Gemini

Toolguard

The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.