Discover +86 AI Security apps & tools

Pros: Supports TCP, UDP, HTTP and WebSocket protocol testing. Integrates with ysoserial and Java-Chains external extensions. Built-in proxy services for Out-of-Band and JNDI interactions. Plugin system with documentation for custom vulnerability modules.

Cons: Requires scripting and security expertise to author useful plugins. AI-driven interaction assists testing but needs human verification. Setup needs a compatible runtime environment as documented.

Pros: Generates an AI Bill of Materials listing agents, tools, and credentials. Scans Terraform and CloudFormation templates for IaC misconfigurations. Provides a runtime gateway to monitor and control agent behavior. Self-hosted deployment via Docker keeps security data on your infrastructure.

Cons: Designed primarily for MCP environments, limiting non‑MCP applicability. Self-hosting requires internal operations and ongoing maintenance. CI/CD focus on GitHub Actions and Docker requires pipeline adaptation.

Pros: Standardized MCP interface for direct AI-agent connectivity. Integrates established tools such as Nmap, ffuf, and Nuclei. Extensible module architecture that accepts custom scripts. Runs on the host via Node.js, using local tooling.

Cons: Requires preinstallation of CLI security tools in the system PATH. Needs an MCP-compliant client and configuration to operate. Geared toward experienced security practitioners and researchers. Agent-driven actions and interpretations require human verification.

Pros: MCP-native integration enables protocol-level request inspection. Open-source repository allows auditing and custom rule development. Performs many checks locally, reducing external data exposure. Modular design integrates with MCP hosts including Claude Desktop.

Cons: Advanced scanning may require external security databases. Integration requires editing MCP client configurations. Better suited to teams with security or developer expertise.

Pros: Local server keeps processed data inside the user's environment. MCP interface lets AI clients call operations during conversation. Includes standard hashing algorithms and AES encryption operations. Curated operation set exposes commonly used CyberChef functions to clients.

Cons: Requires a working Node.js installation and MCP-compatible client. Not every CyberChef operation from the full library is exposed. AI client's interpretation of results must be independently verified. Initial setup requires editing client configuration files.

Pros: Native MCP architecture enables low-latency, context-aware monitoring. Built-in adversarial testing utilities for controlled red-team exercises. Extensible rule engine allows custom security policies and patterns. Open-source GitHub hosting supports community auditing and adaptation.

Cons: Detects known injection patterns but is not a foolproof defense. Requires an MCP-compatible environment and a modern runtime like Node.js. Primarily aimed at developers and security teams, not end users.

Pros: Executes model-generated code inside isolated sandboxes. Directory whitelisting enforces restricted file system access. MCP protocol compatibility with clients like Claude Desktop. Open-source codebase supports community audits and inspection.

Cons: Requires an MCP-compliant client such as Claude Desktop. Depends on a Node.js runtime on host systems. Targeted at a niche audience of MCP developers and researchers. Whitelist configuration requires careful validation before production use.

Pros: Executes Kali utilities and returns machine-readable results. Go implementation designed for efficient resource use. Extensible toolset model for adding custom wrappers. Compatible with MCP clients such as Claude Desktop.

Cons: Requires an existing Kali tools installation on the host. Installation requires cloning and building with the Go toolchain. Live command execution mandates isolated lab deployment. Suited to technically proficient, early-adopter users.

Pros: MCP-native server integrates directly with clients like Claude Desktop. Renames identifiers to reduce human readability of Python source. Strips comments and docstrings to remove non-functional metadata. Preserves execution semantics so obfuscated scripts still run.

Cons: Python-only focus excludes non-Python projects. Requires an MCP-compatible host and local Python environment. Obfuscation is irreversible, complicating post-deployment debugging. Not a complete substitute for legal intellectual-property protections.

Pros: Real-time security scanning for AI agent inputs and outputs. Detection of prompt injection and jailbreak attempts. PII detection and filtering to reduce data leakage risk. Open-source code and community-driven signature model.

Cons: Requires an MCP-compliant host and Node.js runtime. Optimized for agentic workflows, less relevant for simple LLM assistants. Deployment requires repository clone and manual MCP configuration.

Pros: Native MCP server for supplying model context to agents. CLI plus extensible architecture for custom tool integrations. Connects AI agents to security scanners and cloud provider APIs. Open-source repository allows inspection and customization.

Cons: Requires an MCP-compatible host application for agentic workflows. Command-line and Node.js familiarity expected for setup and customization. Generated remediation steps depend on scanner and model quality. Integration relies on available APIs from security tools and cloud providers.

Pros: Executes AI-generated code inside Docker containers to isolate the host system.. Integrates natively with Model Context Protocol clients like Claude Desktop.. Restricts file access to explicitly mapped directories for safer runs.. Open-source repository available for external audit on GitHub..

Cons: Requires Docker installed on the host system to function.. Depends on an MCP-compatible client such as Claude Desktop.. Language support depends on user-provided Docker images.. Node.js-based server needs manual setup and image configuration..

Pros: Forces agent outputs into verifiable drafts before execution. Redacts or masks sensitive fields prior to model access. Optimizes context to reduce prompt injection risks. Open-source hosting enables community auditing and customization.

Cons: Requires an MCP-compatible client or host to operate. Depends on human reviewers, adding operational overhead. Effectiveness relies on correctly defined security policies.

Pros: Protocol-level honeypot tailored for the Model Context Protocol. Captures detailed logs for every tool call and resource request. Lightweight architecture designed for easy deployment in test environments.

Cons: Requires Node.js and an existing MCP environment to run. Primarily intended for monitoring and research, not a standalone production appliance. Logs are emitted to stdout or files, requiring external aggregation for analysis.

Pros: Automated discovery and enumeration of MCP endpoints. Detects sensitive data exposure in context and resource definitions. CLI integration for inclusion in CI/CD pipelines. Open-source codebase allows inspection and contribution.

Cons: Does not automatically remediate identified security issues. Requires a modern Node.js runtime to execute. Scans only endpoints reachable over the network. Narrow scope limited to MCP-standard deployments.

Pros: Exposes KMS encryption, decryption, and signing to MCP agents. Private keys remain inside AWS KMS hardware security modules. Integrates with MCP clients such as Claude Desktop. Supports data key generation for envelope encryption patterns.

Cons: Limited to AWS KMS, not cloud-agnostic. Requires Node.js and configured AWS credentials on host. Agentic cryptography needs careful IAM permission management. Niche audience of MCP early adopters limits broad applicability.