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.
Lets an AI client verify software license compatibility, identify SPDX IDs, and check dependency licenses across multiple package managers.
Performs domain security reconnaissance, phishing detection, and infrastructure analysis for AI agents.
Provides a verifiable identity and authority standard for AI agents to manage permissions, spend limits, and human-in-the-loop escalations.
Provides AI agents with SM2 cryptographic identity, real-name verification via QR codes, and SD-JWT verifiable credential generation.
$claude mcp add realagentmcp -- npx -y realagent-mcp
Performs security auditing for AI agents and MCP configurations by analyzing prompt injection resistance, data flows, and package vulnerabilities.
$claude mcp add mcp-audit-server -- npx -y ledd-mcp-audit-server
Provides runtime security for applications, APIs, and LLMs by enforcing a positive-security model that blocks deviations from normal behavior.
$claude mcp add nemesis-shield-sdks -- npx -y @nemesis-shield-autogon/mcp
Provides threat intelligence and preflight security checks for AI agents to validate wallets, domains, packages, and CVEs before taking action.
$claude mcp add --transport http pg1-ai-agent https://pg1-ai-agent.vercel.app/api/mcp
Allows AI agents to issue signed receipts that verify actions taken and disclose any commercial influences or conflicts of interest.
$claude mcp add recipes -- npx -y @getstub/mcp-check
Exposes a specific folder to AI clients with read-only access protected by a path-containment boundary.
$claude mcp add wyrd-mcp -- npx -y wyrd-mcp
Enables AI clients to perform automated frontend security analysis, including technology stack identification, leak scanning, and vulnerability auditing.
Allows an AI agent to inspect and configure Chrome Enterprise environments, including DLP rules, connector policies, and browser telemetry.
Enables AI assistants to manage Sliver C2 infrastructure, including sessions, beacons, listeners, and implant interactions for red team operations.
Scans AI-generated code for security vulnerabilities like leaked keys, SQL injection, and prompt injection using an offline, zero-telemetry engine.
Enforces role-based access control for AI assistant tools using Cerbos policies to dynamically enable or disable MCP tool access.
Enforces tool access policies, tiers, and mandatory confirmation flags for financial operations within MCP servers.
Enables AI agents to perform identity verification through face comparison, liveness detection, document OCR, and media risk labeling.
$claude mcp add ekyc-suite -- npx -y @wefi-ai/ekyc-suite-mcp
Provides risk-signal analysis for x402 endpoints to help agents detect decoys, zombies, and price traps before making payments.
$claude mcp add x402station-mcp -- npx -y x402station-mcp
Secures AI agents and MCP servers using mTLS certificate identity and DPoP-bound tokens to prevent unauthorized access from leaked credentials.
Provides a trust infrastructure layer for AI agents that implements limits, security checks, and signed audit logs for MCP servers.
Provides a reproducible benchmark to score MCP security guards against a versioned corpus of injection, exfiltration, and tool-poisoning attacks.