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.
Prevents API key and credential leaks by scanning code, git changes, and MCP configurations before they reach AI models or public repositories.
$claude mcp add mcp-secret-sentinel -- uvx mcp-secret-sentinel
Enables AI assistants to drive Sn1per for authorized penetration testing, reconnaissance, and attack surface scanning with scope enforcement.
$claude mcp add sn1per-mcp -- uvx sn1per-mcp
Scans MCP servers and agentic AI components for vulnerabilities, conformance scores, and threat intelligence using the AVE database.
$claude mcp add bawbel-mcp -- uvx bawbel-mcp
Analyzes Google Cloud Armor WAF logs to provide deny summaries, false-positive checks for home regions, and preview rule reviews.
$claude mcp add cloudarmor-mcp -- uvx cloudarmor-mcp
Secures enterprise AI agents through observability, security benchmarking, and threat detection of agentic behavior.
Connects AI agents to CrowdStrike Falcon so they can query detections, threat intelligence, hosts, and vulnerabilities.
$claude mcp add falcon-mcp -- uvx falcon-mcp
Lets an AI client manage Apache Superset dashboards, charts, datasets, SQL Lab queries, users, roles, and row-level security.
$claude mcp add mcp-superset -- uvx mcp-superset
Provides a tamper-evident audit trail and policy gating for autonomous AI agent actions to ensure accountable autonomy.
$claude mcp add vaara-server -- uvx vaara
Provides a centralized HTTP gateway for AI agents to perform controlled SSH commands and SFTP file transfers with audit logging and command policies.
$claude mcp add ssh-mcp -- docker run -i --rm ghcr.io/gelse/ssh-mcp:0.3.0
Acts as a security proxy for MCP servers to provide behavioral profiling, security scanning, and risk gating for tool execution.
$claude mcp add mcpsafetywarden -- uvx mcpsafetywarden
Provides a read-only audit trail of security findings, test coverage, and repair status to help developers review agent-generated code changes.
$claude mcp add code-factory -- uvx factoryline-code-factory
Lets an AI agent query a local dependency graph to identify how code changes affect routes, calls, tables, and configurations.
$claude mcp add code-graph -- uvx cg-code-graph
Enforces policy checks for AI agent writes with ALLOW, DENY, or STEP_UP decisions and a tamper-evident audit log.
$claude mcp add writ -- uvx writ-mcp
Enables AI agents to sign, verify, encrypt, and decrypt OpenPGP messages without exposing private keys to the agent.
$claude mcp add gpg-mcp -- uvx gpg-mcp
Enables AI agents to perform OSINT discovery of public emails, subdomains, hostnames, IPs, and LinkedIn profiles for a target domain.
$claude mcp add theharvester-mcp -- docker run -i --rm docker.io/devkind/theharvester-mcp:1.0.0
Connects your existing Unix pass or GPG password store to AI tools with read-only defaults and strict security controls.
$claude mcp add unix-pass-mcp -- uvx unix-pass-mcpEnforces commit-time policy checks for AI agent writes with ALLOW, DENY, or STEP_UP decisions and a tamper-evident audit log.
$claude mcp add writ -- uvx writ-mcp
Enables natural language security investigations using Microsoft Sentinel, Defender XDR, and threat intelligence via specialized agent skills.
Lets AI clients list and retrieve Zscaler Zero Trust Exchange resources across ZPA, ZIA, ZDX, ZCC and more, with opt-in write tools.
$claude mcp add zscaler-mcp-server -- uvx zscaler-mcp
Lets an AI client browse and administer Active Directory over LDAP, covering users, groups, computers, OUs and security audits.