Security MCP servers

Scan code for security vulnerabilities using Semgrep.

IDA Pro plugin for binary analysis: decompilation, disassembly and automatic malware analysis reports.

Autonomous reverse engineering with Ghidra: decompile binaries, rename methods and data, and list methods, classes, imports and exports.

Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.

Search the Claude Code Ultimate Guide, official Anthropic documentation, releases, examples, security references, agent harness data, and translations from any MCP-compatible client.

JADX decompiler plugin providing live, LLM-assisted reverse engineering.

A lightweight utility designed to simplify the deployment and management of MCP servers, ensuring ease of use, consistency, and security through containerization

Honeypot framework for building decoy MCP tools that an agent would never use in normal work, to detect prompt injection and malicious agent behavior.

MCP server for JavaScript analysis, security auditing, browser automation and hooks

AI-powered OSINT agent & MCP server. 21 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.

MySQL database integration with configurable access controls, schema inspection and security guidelines.

Locally check npm and PyPI packages, such as those suggested by AI coding tools, for vulnerabilities and malicious code.

Dead code detection, security scanning and code quality analysis for Python, TypeScript and Go, with AI-assisted remediation.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

Native Ghidra integration with GUI configuration, logging and no external dependencies.

Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.

Enable AI agents to secure code with Semgrep.

Automate reverse engineering of Android APKs with Apktool.

Requires a named human's approval before irreversible agent actions such as payments or deploys, then issues an offline-verifiable Ed25519 trust receipt.

Blitz Strike — a universal MCP security-audit toolbelt. BLITZ sweeps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE verifies live. 57 attack chains, 130-tool catalog, intelligence data layer. One server, every agent.

A Binary Ninja plugin, MCP server, and bridge that seamlessly integrates Binary Ninja with your favorite MCP client.

Android device control, debugging, system analysis and UI automation, with a security framework.

Local MCP proxy that routes multiple servers through one endpoint, with BM25 tool filtering, quarantine security, activity logging and a web UI.

integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language queries instead of Cypher.

Disassemble and inspect binaries for reverse engineering with the Radare2 disassembler.

Fail-closed approval layer for unattended agent runs: checks actions against org policy, requests human approval and logs every decision to a causal ledger.

Wireshark packet analysis: capture, protocol statistics, field extraction and security analysis.

Verifiable execution protocol for agent tool calls: signed policy decisions, causal evidence chains and offline verification from a SQLite ledger.

MCP server for Niubiz — Peru card acquirer: security token, session, authorize, reverse

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

Search usernames across social networks and analyze URLs with maigret, an OSINT tool that collects account information from public sources.

Connects AI agents with CrowdStrike Falcon for security analysis and automation.

Access real-time security alerts and event data from Wazuh SIEM.

Security testing toolbox that combines open source tools behind a single interface for pentesting, bug bounty hunting and threat hunting.

AI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

Security scanner for AI agent tools. Local static scan of MCP IDE configs (41 rules, toxic flow heuristics, AAuth visibility, auto-fix, tool pinning). Optional proxy + in-browser dashboard: traffic, findings, AAuth Explorer, YARA, Playground. Smart Scan o

Command-line execution with customizable security policies.

Query the Shodan API and Shodan CVEDB: IP lookups, device searches, DNS lookups, vulnerability queries and CPE lookups.

Author, lint, validate and convert Sigma detection rules with RSigma, evaluate and explain detections against log events, and inspect correlation state.

Query the VirusTotal API: scan URLs, analyze file hashes and retrieve IP address reports.

Ghidra plugin for binary analysis: function inspection, decompilation, memory exploration and import/export analysis.

Agent security middleware with layered defenses: prompt injection detection, DLP data flow tracking, command blocking and PII detection.

MCP server for security scanning — structured Trivy, Semgrep, and Gitleaks findings for AI agents

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

SQL validation, formatting, parsing, linting, security scanning and metadata extraction across multiple SQL dialects.