agentshield (affaan-m/agentshield) is an open-source AI project on GitHub. Repository summary: AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️ Its focus includes MCP and tool-calling integration, developer-centric engineering workflows, security and compliance automation. It is suitable for extension, integration, and iterative delivery in real workflows.
License
MIT
Stars
646
Features
- Core capability: AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
- Provides MCP or tool-calling integration
- Built for code generation, debugging, or engineering integration
- Covers security testing, risk detection, or compliance workflows
- Repository: affaan-m/agentshield
- Primary language: TypeScript
Use Cases
- Connects external systems into agent workflows
- Supports AI engineering build-and-iterate workflows for dev teams
- Used for security assessment and compliance automation
- Build internal AI workflow prototypes with agentshield
- Validate agentshield in production-like engineering scenarios
- Building AI development workflows
FAQ
Teams should first define integration boundaries and call patterns, then map repository capabilities into concrete interfaces, parameters, and access rules. GitHub repository: https://github.com/affaan-m/agentshield. Community traction is around 646 stars. License: MIT.
It usually works as an execution component or capability layer, with common deployment fits such as: Connects external systems into agent workflows, Supports AI engineering build-and-iterate workflows for dev teams, Used for security assessment and compliance automation.
