Security MCP servers for scanning, threat intelligence and audits: let an AI assistant check code, dependencies and infrastructure for risks. 3,537 servers in this category.
Enables AI agents to perform security configuration validation, documentation searches, and live threat detection within the Guard ecosystem.
$claude mcp add guard-core-mcp -- uvx guard-core-mcp
Provides a local-first privacy layer that detects and redacts PII, credentials, and sensitive data before it reaches AI models or external tools.
$claude mcp add securedact-mcp -- uvx securedact-mcp
Verifies AI agent actions through multi-model adversarial consensus and provides signed, cryptographically verifiable decision receipts.
$claude mcp add ethersflow -- npx -y @ethersflow/mcp-server
Detects prompt injection, jailbreaks, and data exfiltration in untrusted text before it reaches an LLM.
$claude mcp add safeprompt -- npx -y @safeprompt.dev/mcp
Provides an enterprise-grade security template for MCP servers featuring role-based access control, allowlists, and human confirmation for destructive actions.
$claude mcp add mcp-agent-template -- uvx mcp-agent-template
Performs username, email, and phone number lookups using over 9,700 modules from 19 open-source OSINT projects.
Lets an AI client run OSINT investigations across domains, IPs, images and breaches, and save findings in a local evidence graph.
Evaluates AI agent proposals against thirteen constitutional floors to provide governed verdicts and auditable receipts before execution.
$claude mcp add arifos-9ba036 -- uvx arifos
Audits an MCP server and returns a 0–100 score with cited, fixable findings on protocol, tools, and security.
$claude mcp add mcpscore -- npx -y @mcp-box/mcpscore
Allows AI assistants to manage OPNsense firewalls, including firewall rules, network settings, DNS, DHCP, and VPN configurations.
Extracts indicators of compromise from text and analyzes them with Cyberbro threat-intelligence engines.
$claude mcp add mcp-cyberbro -- uvx mcp-cyberbro
Enables AI assistants to perform advanced binary analysis, decompilation, and reverse engineering using Ghidra's headless analyzer.
Acts as a self-hosted MCP gateway that pins tool schemas, enforces per-call policy, and holds risky calls for approval.
$claude mcp add mcp-hangar -- uvx mcp-hangar
Provides a verifiable audit trail and policy gating for autonomous AI agent actions to ensure accountability and regulatory compliance.
$claude mcp add vaara -- uvx vaara
Acts as a secure gateway and quarantine for AI agent traffic, providing three-layer prompt injection defense and token optimization.
$claude mcp add mcp-trentina -- uvx mcp-trentina-crunchtools
Enables AI assistants to query Microsoft security updates, CVE details, and CISA KEV enrichment via the MSRC API.
$claude mcp add patch-tuesday-mcp -- uvx patch-tuesday-mcp
Lets AI agents run classic OSINT tools locally to perform username searches, email lookups, domain scans, and metadata analysis.
$claude mcp add osint-toolbox-mcp -- uvx osint-toolbox-mcp
Converts security evidence into traceable control assessments and reviewable audit workpapers using a common control framework.
$claude mcp add grc-lake -- uvx grc-lake
Lets an AI client view and control local IP cameras through snapshots, video recordings, pan/tilt movements, and change detection.
$claude mcp add ipcam-mcp -- uvx ipcam-mcp
Enforces session-based business logic constraints and budget ceilings on AI tool calls through a policy-driven gateway.
$claude mcp add clayseal-capabilities -- uvx clayseal