- SI Score
- 70/100
- Pricing
- Not confirmed
- Free plan
- Not confirmed
- Sign-up required
- Not confirmed
Ask SI about MCP Defender
Answers use saved listing facts and recorded sources.Homepage screenshot
What it does
MCP Defender is a security tool that acts as a proxy between AI applications and MCP servers. It analyzes communications in real time to find threats such as prompt injection, tool poisoning, credential theft, and command injection. It supports Cursor, Claude, Visual Studio Code, and Windsurf.
MCP Defender is a security proxy for developers who run AI coding assistants and want a check on MCP tool calls. It sits between your AI apps and MCP servers and analyzes all communications in real time. Detection combines LLM analysis with deterministic signatures, and it covers prompt injection, tool poisoning, credential theft, and command injection. You can use your preferred LLM provider and your own API keys. The project is open source under AGPL-3.0. Cursor, Claude, Visual Studio Code, and Windsurf are supported. The site states that MCP Defender has been acquired by Docker Inc., so future development and support terms are worth watching. No pricing page was found, so cost and plan details are unknown.
- Scans MCP tool calls and responses in real time
- Supports Cursor, Claude, Visual Studio Code, and Windsurf
- Open source under AGPL-3.0 and works with your own LLM keys
- No pricing page was found on the site
- Only four AI apps are listed as supported
- Detection quality depends on the LLM provider you configure