Ronin Defense MCP
Detects and sanitizes hidden-payload attacks in MCP communications to protect LLMs in agentic IDEs from malicious prompt injection and adversarial content delivery.
README
CS8803_MLSecurity_MCP_Defense_Server
An MCP defense server prototype for detecting and sanitizing hidden-payload delivery to LLMs in agentic IDEs (e.g., Cursor). Built exclusively for ML security research and defensive hardening - no malicious use.
How is the MCP server hosted?
The MCP server is hosted on the cloud thanks to FastMCP Cloud. You can view the current deployment of the server at https://fastmcp.cloud/ronin-mcp/ronin-defense-mcp-v1/deployments. Whenever you commit and push a change to the main branch, it will automatically build and deploy onto the cloud. Please note that this link is only accessible to the owners of this project.
How to configure the MCP server for Cursor?
Go to File -> Preferences -> Cursor Settings -> Tools & MCP -> Installed MCP Servers. Create a new MCP server configuration using the following json:
{
"mcpServers": {
"ronin-defense-mcp-v1": {
"url": "https://ronin-defense-mcp-v1.fastmcp.app/mcp",
"headers": {}
}
}
}
Then, go back to Installed MCP Servers and refresh ronin-defense-mcp-v1 until the light is green and it shows the tools associated with the Ronin MCP server. If you had originally configured and turned on ronin-mcp-v1, please make sure that one is turned off in Cursor's Installed MCP Servers page because ronin-defense-mcp-v1 is a proxy for that malicious server. In Cursor, open the AI Panel and try the following prompt to see if the server connection is successful:
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.