mcp-fence is an open-source CLI tool for security scanning, protocol inspection, dynamic fuzzing, and sandboxed testing of Model Context Protocol (MCP) servers. It helps AI infrastructure engineers identify vulnerabilities and generate security reports.
In the Infrastructure & Backend space, mcp-fence takes a focused approach. It enables developers to test and secure Model Context Protocol servers with local-first scanning and fuzzing tools. It is built as an open-source project for AI infrastructure and security engineers. mcp-fence is open source under the Apache-2.0 license. It runs on the web and the command line, and it can be self-hosted.
Daoyuan Li builds and maintains mcp-fence, and it first shipped in 2026. Development happens publicly on GitHub with 20 stars and 38 commits in the last 90 days. Key capabilities include security scanning, protocol inspection, and dynamic fuzzing. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do