A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.
This server has not been audited yet. Trust score will appear once the first audit completes.
Tool-Details folgen in Kürze. Dieser Server hat 0 Tools verfügbar.
A proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.
Yes, Cursor Agent Poisoning is completely free to use with no usage limits on the free tier.
Cursor Agent Poisoning is listed under the AI & Machine Learning category in the AgentForge MCP registry.
Cursor Agent Poisoning has a current uptime of 99.9% with an average response time of 0ms.
To connect Cursor Agent Poisoning, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Cursor Agent Poisoning's tools via the Model Context Protocol.