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.
A secret broker that allows AI agents to resolve and inject secrets at the execution boundary without exposing raw values to the LLM context.
$claude mcp add portunus -- docker run -i --rm ghcr.io/mdostal/portunus:0.34.0
Fingerprints websites to identify CMS, web servers, frameworks, and analytics tools using WhatWeb in a sandboxed Docker container.
$claude mcp add whatweb-mcp -- docker run -i --rm docker.io/devkind/whatweb-mcp:1.0.0
Provides trust infrastructure for AI agents through tools for trust scoring, compliance enforcement, and PII/secret protection.
$claude mcp add veriswarm-sdk -- uvx veriswarm-mcp
Enables AI agents to perform governed operations, diagnostics, and root cause analysis on OPNsense and pfSense firewalls.
$claude mcp add firewall-aiops -- uvx firewall-aiops
Performs sub-3ms image forensics to detect deepfakes, generative AI inpainting, and physical tampering using OpenCV 5 and mathematical sensor analysis.
$claude mcp add verisight -- uvx verisight
Enables AI assistants to perform real-time DNS security analysis, including DNSSEC validation, email authentication audits, and registration intelligence.
$claude mcp add dns-mcp -- docker run -i --rm docker.io/mclose/dns-mcp:1.3.4
Verifies the supply-chain trust of AI agents, frameworks, and MCP servers using a public trust registry.
$claude mcp add hvtracker-mcp -- npx -y hvtracker-mcp
Validates business leads and crypto wallets by checking official registers, EU VAT, and global sanctions lists.
$claude mcp add --transport http limitguard-mcp https://api.limitguard.ai/mcp
Provides signed, offline-verifiable attestations and security gates for agent components like MCP servers and agent skills.
$claude mcp add canari -- uvx canari-mcp
Lets an AI client check software packages for CVEs, slopsquatting, and CISA KEV status during code generation.
$claude mcp add vdb-mcp -- uvx vdb-mcp
Centralizes AI development tools by providing a governed control plane for MCP servers, agents, and skills with secure OAuth authentication and discovery.
Scans code for leaked secrets, triages and remediates incidents, and manages honeytokens via GitGuardian's API.
Manages FortiGate firewalls from an AI client: firewall policies, address objects, routing, VPN, and read-only monitoring.
Enables AI clients to perform automated penetration testing, red-teaming, and cybersecurity orchestration using a large collection of security tools.
Routes tasks to a specific subset of skills, MCP servers, and tools to optimize context windows and prevent prompt injection.
$claude mcp add lockkeeper -- uvx lockkeeper
Provides a read-only semantic layer and security firewall between AI agents and databases to prevent unauthorized writes and PII leaks.
$claude mcp add schemabrain -- uvx schemabrain
An automated security scanner that audits MCP servers for prompt injection, credential leaks, SSRF, and tool poisoning vulnerabilities.
Expose the BunkerWeb API to MCP clients to manage services, instances, bans, configuration snippets, plugins, and scheduler jobs.
Checks AI-generated code for security vulnerabilities, complexity issues, and configuration drift before deployment.
$claude mcp add --transport http agents-hefesto https://hefestoai.narapallc.com/api/mcp-protocol
Enables AI agents to perform compiler-precise code property graph analysis and data flow tracking across C, Python, and TypeScript.
$claude mcp add lachesis -- uvx lachesis-cpg