by AIS2Lab · MCP Server · ★ 30
MCPSecBench This benchmark includes and used in our experiment. A technical report is available as follows: Overview of MCPSecBench main.py: an automated testing script including part attacks. addserver.py: normal server for computation. maliciousadd.py: malicious server. download.py: a normal server for checking signature. squatting.py: a malicious server for server name squatting. client.py: client that connect with MCP host and server. At present, it support OpenAI and Claude. It can be extended for Deepseek, Llama, and QWen. mitm.py: the script that implements Man-in-the-Middle attack.
| Stars | 30 |
| Forks | 8 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65.3392396995175/100 |
| Last Updated | 2026-03-04 |
| Created | 2025-08-09 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~526k |
Explore other popular mcp server tools:
MCPSecBench is MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols. It is categorized as a MCP Server with 30 GitHub stars.
MCPSecBench is primarily written in Python. It covers topics such as benchmark, llm-agent, mcp.
You can find installation instructions and usage details in the MCPSecBench GitHub repository at github.com/AIS2Lab/MCPSecBench. The project has 30 stars and 8 forks, indicating an active community.
MCPSecBench is released under the MIT license, making it free to use and modify according to the license terms.