MCP Poisoning Attack - PoC
This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.
Directory
This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.
A repository dedicated to exploring, experimenting with, and applying Generative AI concepts and tools in practical, everyday scenarios.
Integrates with Babashka to enable dynamic Clojure code execution and interaction for scripting, data processing, and system automation tasks.
An AI assistant for development tasks, including taking screenshots, architecting solutions, and performing code reviews.
Provides specialized backup and restoration for code editing tools, creating timestamped snapshots with contextual metadata that preserve both file content and…
Connects to Compiler Explorer API for listing programming languages, retrieving available compilers, and compiling source code with customizable options…
Enables intelligent code analysis and debugging through the Perplexity AI's API, offering detailed error analysis, pattern detection, and comprehensive…
A knowledge management tool for code repositories using vector embeddings, powered by a local Ollama service.
An innovative Model Context Protocol hub that seamlessly connects your client with intelligent agents, enabling powerful cross-platform communication across…
Enables seamless deployment of containerized applications directly from code editors through a three-step workflow of GitHub authentication, repository setup…
It controls WeChat Developer Tools and mini‑programs/mini‑games via the Model Context Protocol (MCP). It works with Claude Desktop, Cursor, Windsurf, and any…
A Model Context Protocol (MCP) server that provides tools to query BrasilAPI across different clients and LLMs. Enhance your AI apps with rich data from Brasil…
Integrates with Azure DevOps to enable querying work items, creating tasks, searching code repositories, and retrieving project information without context…
The cosense-mcp-server facilitates the integration with Claude Desktop by serving as a middleware command pipeline server, allowing for interaction with…
Bridges Microsoft's AutoGen framework with external tools, enabling autonomous agents to execute code, perform research, and collaborate in multi-agent…
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Remote server: https://fitllm.run/api/mcp
Integrates with the qrencode utility to generate QR codes dynamically, supporting various output formats and configuration options for flexible use in…
Integrates with Perplexity AI to enable context-aware conversations, research, and code analysis through natural language processing capabilities.
Provides AI-assisted development tools for semantic routing, code generation, refactoring, and project management with intelligent request handling and…
# Supavec MCP Server A [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that enables AI assistants to fetch relevant embeddings and…
Provides Language Server Protocol (LSP) capabilities through multilspy, enabling code intelligence features like finding definitions, references, completions…
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
GovQL is an MCP (Model Context Protocol) server that provides AI clients such as Claude Desktop, Claude Code, and Cursor with direct access to the US…
Self-improving MCP memory server for AI agents. One command, no cloud, no config. Hybrid search, feedback loop quality system, dashboard UI, auto-linking…