MCP_TOOL_POISONING_ATTACKS
A Node.js project demonstrating MCP client and server interactions for tool poisoning attacks, requiring an Anthropic API key.
Directory
A Node.js project demonstrating MCP client and server interactions for tool poisoning attacks, requiring an Anthropic API key.
A server for the Microsoft Graph and Azure RM APIs to manage Azure and Microsoft 365 tenants with AI.
Hosted Streamable HTTP MCP server for IP intelligence, fraud risk scoring, email validation, DNS, WHOIS, domain age, quota, and usage tools for AI agents.
EU legal research for AI agents: semantic + full-text search over ~48,000 EUR-Lex acts including consolidated versions, daily drift monitoring, answers with…
Scan APIs for security vulnerabilities and get OWASP risk scores. Detects auth bypass, BOLA/IDOR, data exposure, prompt injection, and 12+ security categories.
GoPlus Security is the leading Web3 security layer, providing comprehensive protection for multiple blockchain ecosystems. This project provides a MCP server…
CloudSword is an open-source tool designed to help public cloud tenants quickly discover, test, and improve security in their cloud environments. Targeted at…
An MCP server to run arbitrary commands on the local machine.
A backend-to-frontend bridge that securely exposes MCP servers to the internet, supporting agent authentication, content analysis, transformation, and…
Provides a bridge to Google Keep for searching, creating, updating, and deleting notes with safety features that restrict modifications to specifically labeled…
AI constraint engine — persistent memory + active enforcement. Stops AI from breaking locked code. Semantic conflict detection, file-level guards, session…
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
Integrates with Obsidian vaults, enabling natural language queries and updates to notes through secure read/write access.
Official Model Context Protocol (MCP) server for vatnode — EU VAT validation, rates, and format checks for AI agents (Claude, Cursor, ChatGPT).
Enables interaction with WebDAV file systems through natural language commands, providing complete CRUD operations for files and directories with support for…
Official MCP server for OpenSOSData - real-time US business entity search across all 53 jurisdictions (all 50 states + DC + Puerto Rico + US Virgin Islands)…
This tool creates an MCP server to bridge the gap between AI workflows and EMBA security analysis.
An MCP server deployed on Cloudflare Workers, featuring OAuth login support.
A remote MCP server running on Cloudflare Workers with OAuth login support.
A remote MCP server deployable on Cloudflare Workers with OAuth login support, using Cloudflare KV for data storage.
An MCP server for Keycloak administration, offering over 30 tools to manage users, realms, clients, roles, and more from AI assistants.
Performs a Trivy scan to produce a Software Bill of Materials (SBOM) in CycloneDX format.
A remote MCP server deployable on Cloudflare Workers with OAuth login support, using Cloudflare KV for data storage.
Lucairn is an EU-based privacy gateway that sits between your MCP-enabled agent and the upstream LLM (Claude, GPT-4o, o1/o3/o4).