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.
Analyze customer feedback by stripping PII before processing to find stable themes and provide cited evidence for AI agents.
$claude mcp add obsei -- uvx obsei
Analyzes PCAP capture files for DNS, DHCP, ICMP, TCP, SIP, and file metadata using protocol-specific tools.
$claude mcp add mcpcap -- uvx mcpcap
Lets an AI client query Wazuh SIEM alerts, agents, vulnerabilities and compliance data, and dispatch active responses.
Issues signed agent identities, verifiable credentials, and governance audit evidence that AI clients can create and verify offline.
$claude mcp add attestix -- uvx attestix
Lets an AI client check emails and domains against known data breaches, view breach analytics, and browse breach metrics.
$claude mcp add --transport http xposedornot-api https://api.xposedornot.com/mcp
Allows AI agents to query Android APK and DEX files using SQL to analyze classes, methods, strings, and smali code.
$https://github.com/LSPosed/dexsql-release/releases/download/v0.1.1/dexsql.mcpb
Bridges AI clients to any FHIR server so they can search and retrieve clinical healthcare resources.
$claude mcp add fhir-mcp-server -- uvx fhir-mcp-server
Lets AI clients investigate threats, run SOAR actions, query Google Threat Intelligence, and audit cloud security findings in Google SecOps.
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 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
Screens an AI agent's memory writes and reads through detectors and a declarative policy to block poisoning attacks.
Lets an AI client manage a pfSense firewall in natural language: rules, NAT, VPN, DNS, DHCP, certificates and diagnostics, with safety guardrails.
Connects AI coding assistants to Snyk API & Web to onboard scan targets, run DAST scans, and triage security findings using natural language.
$claude mcp add saw-mcp -- uvx snyk-apiweb-mcp
Accelerates cloud security workflows by providing AI skills for alert triage, impact analysis, compliance gap identification, and guided remediation.
Scans MCP configurations and source code to detect exposed secrets, shadow APIs, and code-level vulnerabilities in AI agent tools.
Maps and governs AI attack surfaces in application code by detecting LLM calls, agents, MCP servers, and RAG pipelines locally and offline.
Evaluates agentic AI applications through prompt injection testing, vulnerability assessment, SBOM generation, and static analysis.
Discovers and analyzes Model Context Protocol servers using Shodan to identify publicly exposed AI infrastructure and tool capabilities.
Enables LLM agents to perform autonomous binary research and exploit development using GDB and pwndbg in an isolated environment.
Demonstrates security vulnerabilities in the Model Context Protocol and provides defensive frameworks to mitigate tool poisoning attacks.