Security MCP servers for scanning, threat intelligence and audits: let an AI assistant check code, dependencies and infrastructure for risks. 3,541 servers in this category.
Enables AI clients to orchestrate professional penetration testing workflows on Kali Linux with enforced scope, VPN, and audit guardrails.
Performs local byte-wrangling, cryptographic hashing, encoding, and Ethereum primitive computations without remote API calls.
Analyzes EVM token security by checking approvals, signatures, and simulated buy/sell routes to identify honeypots and impostor tokens.
An agent harness that enables LLMs to perform authorized bug-bounty reconnaissance and vulnerability detection through scope-enforced, human-gated tools.
A security gateway that provides OAuth 2.1 validation, RBAC, rate limiting, and tool-definition pinning for Model Context Protocol servers.
Tests MCP server authorization implementations against the 2026-07-28 specification using naive and hardened reference models.
Acts as an OAuth 2.1 reverse proxy that validates Entra ID tokens, enforces tool-level RBAC, and maintains hash-chained audit logs for MCP servers.
Provides a hardened OIDC-style authentication layer for MCP servers using pure Python standard library features.
Provides a measurement rig to evaluate how policy gates, action monitors, and approval steps prevent adversarial incident-response agents.
Provides a reference implementation for a secure enterprise healthcare MCP platform using synthetic FHIR data and multi-tier identity enforcement.
Redacts PII, PHI, and financial data locally using Microsoft Presidio before it is sent to AI clients like Claude.
Runs untrusted repositories, packages, or MCP servers in a sandbox with fake credentials to detect malicious behavior and data exfiltration.
Provides a multi-user MCP gateway with per-user OAuth authentication and team-scoped RBAC for COS Core, Desktop, and Plugins.
Verifies video authenticity by analyzing power-grid frequency flicker using OpenCV 5 and matching it against grid reference logs.
Provides an offline security shield for AI agents to scan MCP servers for vulnerabilities and monitor real-time tool usage.
Performs static security scanning on MCP servers and AI agents to detect code execution risks, SSRF, prompt injection, and hardcoded secrets.
Acts as a security proxy between AI agents and MCP servers to hold risky tool calls for human approval and maintain a verifiable ledger.
Provides a local AI-native workstation for security practitioners to manage evidence, security intelligence, and knowledge via 19 MCP tools.
Provides an automated trust scorecard for MCP servers based on security signals and maintenance activity.
Instruments APIs and AI agents to monitor tool calls, LLM traffic, and security events for threat detection.
