Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Scan MCP servers for potential threats & security findings.
| Date | Stars |
|---|---|
| 2026-08-04 | 1003 |
| 2026-08-06 | 1003 |
| 2026-08-13 | 1027 |
| 2026-08-18 | 1040 |
| 2026-08-19 | 1041 |
| 2026-08-20 | 1045 |
| 2026-08-22 | 1046 |
| 2026-08-23 | 1046 |
| 2026-08-24 | 1046 |
| 2026-08-25 | 1047 |
| 2026-08-26 | 1050 |
| 2026-08-27 | 1051 |
| 2026-08-29 | 1051 |
| 2026-08-30 | 1052 |
| 2026-08-31 | 1056 |
| 2026-09-01 | 1057 |
| 2026-09-02 | 1058 |
| 2026-09-04 | 1060 |
| 2026-09-05 | 1061 |
| 2026-09-06 | 1062 |
| 2026-09-07 | 1066 |
| 2026-09-09 | 1069 |
| 2026-09-10 | 1070 |
| 2026-09-12 | 1071 |
| 2026-09-15 | 1071 |
| 2026-09-16 | 1074 |
| 2026-09-20 | 1073 |
| 2026-09-22 | 1074 |
| 2026-09-23 | 1075 |
| 2026-09-24 | 1075 |
| 2026-09-25 | 1079 |
| 2026-09-27 | 1080 |
| 2026-09-28 | 1081 |
| 2026-09-29 | 1082 |
| 2026-09-30 | 1083 |
| 2026-10-02 | 1083 |
| 2026-10-03 | 1083 |
| 2026-10-04 | 1082 |
| 2026-10-05 | 1083 |
| 2026-10-06 | 1084 |
| 2026-10-07 | 1086 |
| 2026-10-09 | 1088 |
| 2026-10-10 | 1089 |
| 2026-10-13 | 1091 |
| 2026-10-14 | 1091 |
| 2026-10-15 | 1091 |
| 2026-10-16 | 1093 |
| 2026-10-17 | 1094 |
| 2026-10-19 | 1094 |
| 2026-10-20 | 1095 |
| 2026-10-21 | 1096 |
| 2026-10-23 | 1096 |
| 2026-10-25 | 1097 |
| 2026-10-26 | 1098 |
| 2026-10-27 | 1099 |
| 2026-10-28 | 1100 |
| 2026-10-29 | 1102 |
| 2026-10-30 | 1103 |
| 2026-10-31 | 1104 |
| 2026-11-02 | 1106 |
| 2026-11-03 | 1106 |
| 2026-11-04 | 1105 |
Today
-1 stars today
This week
+5 stars this week
This month
+22 stars this month
Momentum
40.0
growth rate 0.46%/day
# MCP Scanner [](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/downloads/) [](https://pypi.org/project/cisco-ai-mcp-scanner/) [](https://discord.com/invite/nKWtDcXxtx) [](https://www.cisco.com/site/us/en/products/security/ai-defense/index.html) [](https://learn-cloudsecurity.cisco.com/ai-security-framework) A Python tool for scanning MCP (Model Context Protocol) servers and tools for potential security findings. The MCP Scanner combines Cisco AI Defense inspect API, YARA rules and LLM-based analysis to detect malicious MCP tools. ## Overview The MCP Scanner provides a comprehensive solution for scanning MCP servers and tools for security findings. It leverages three powerful scanning engines (Yara, LLM-based analysis, Cisco AI Defense) that can be used together or independently. The SDK is designed to be easy to use while providing powerful scanning capabilities, flexible authentication options, and customization.  ## Features - **Multiple Modes:** Run scanner as a stand-alone CLI tool or REST API server - **Multi-Engine Security Analysis**: Use all three scanning engines together or independently based on your needs. - **Vulnerable Packages Scanning**: Scan Python dependencies for known vulnerabilities (CVE/PYSEC/GHSA) using pip-audit integration. - **Readiness Scanning**: Zero-dependency static analysis for production readiness issues (timeouts, retries, error handling). - **Comprehensive Scanning**: Scan MCP tools, prompts, resources, and server instructions for security findings - **Behavioural Code Scanning**: Scan Source code of MCP servers for finding threats. - **VirusTotal Binary Scanning**: Automatically detect malware in binary files (images, PDFs, executables, archives) bundled with MCP servers using VirusTotal hash lookups. - **PyPI Package Scanning**: Download and scan PyPI packages inside a Docker sandbox with behavioral analysis. - **Behavioural Code Scanning**: Scan Source code of MCP servers for detecting threats. - **Static/Offline Scanning**: Scan pre-generated JSON files without live server connections - perfect for CI/CD pipelines and air-gapped environments - **Explicit Authentication Control**: Fine-grained control over authentication with explicit Auth parameters. - **OAuth Support**: Full OAuth authentication support for both SSE and streamable HTTP connections. - **Custom Endpoints**: Configure the API endpoint to support any Cisco AI Defense environments. - **MCP Server Integration**: Connect directly to MCP servers to scan tools, prompts, and resources with flexible authentication. - **MCP 2.0 Protocol Support**: Negotiates modern protocol (`2026-07-28` via `server/discover`) with automatic fallback to legacy `initialize()` for older servers — remote HTTP/SSE and stdio. - **Customizable YARA Rules**: Add your own YARA rules to detect specific patterns. - **Comprehensive Reporting**: Detailed reports on detected security findings. ## Installation ### Prerequisites - Python 3.11+ - uv (Python package manager) - **MCP Python SDK** (`mcp>=2.0.0`, bundled with this package). Live scans negotiate `2026-07-28` when the server supports it and fall back to legacy handshake versions automatically. - A valid Cisco AI Defense API Key (optional) - LLM Provider API Key (optional) - VirusTotal API Key (optional, for binary file malware scanning) ### Installing as a CLI tool ```bash uv tool inst
Excerpt of 36,828 characters
Read on GitHub
61
14
Sanket Mendapara · Cisco Systems, Inc · United States
13
6
3
3
3
Debbie Philips · AWS · United States
2
2
2
2
1
1
1
1
1
Barry Yuan · Cisco · United States
1
Keith O'Brien · Cisco
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9efc2c61f48f1288, topic:mcp, desc:mcp servers
matched fp:9efc2c61f48f1288, topic:agents