"Understanding How to Use a Browser" matching MCP servers:

Enables AI agents to control a local Chromium browser via CDP for page snapshots, screenshots, human-like interactions, autonomous crawling, API/GraphQL reconnaissance, authenticated differential testing, and Burp-like intercept, repeater, and intruder workflows with scope enforcement and audit logging.

Security-focused Firefox browser MCP server for penetration testing, built on Playwright, enabling vulnerability scanning, session manipulation, network inspection, and reconnaissance.

Read-only observation of a single live URL: parses static HTML to report security posture, forms, links, accessibility signals, and leaks, with described fixes. SSRF-gated and safe, never executes JavaScript.

Enables AI coding agents to audit websites for PHP runtime vulnerabilities, compile a live Zero-PHP Next.js App Router replacement preview from a WordPress/PHP site, and retrieve remediation guidance.

Wraps Kali Linux penetration testing tools for authorized security assessments, driven by a local LLM via LM Studio.

MCP server that bridges opencode into Firefox, enabling page reading, JavaScript execution, and security auditing directly from the terminal.

Security for the MCP servers you use: detects tool poisoning, rug pulls, shadowing, secrets and supply-chain risk (OWASP MCP Top 10), with runtime guards and approved-server policy. Runs locally.

Gives AI agents a browser that bypasses bot detection, a MITM proxy for traffic interception, and a Python sandbox to autonomously write and execute security exploits.

Enables interactive Ghidra reverse-engineering inside an AI client by rendering live decompiler, function browser, and call graph views. Users can click symbols to rename them and follow calls to navigate, all without leaving the conversation.

Enables AI agents to perform read-only forensic triage of Windows disk images over MCP stdio, currently offering MD5/SHA-256 hash calculation and verification confined to an evidence root. Every returned finding carries six-field provenance metadata, while a code-enforced security contract guarantees read-only evidence access, no network or shell use at runtime, structured errors, and an append-only JSONL audit trail.

Chrome browser JS reverse engineering MCP tool for CTF/Web security, enabling dynamic analysis and restoration of login encryption logic.

Connects AI assistants to AttackForge's Self-Service API with full endpoint coverage, response size optimization, and local caching for efficient use in long conversations.

Enables LLM-powered browser automation and security testing with features like browser management, network monitoring, DOM manipulation, and captcha handling.

Wraps the recon CLIs security researchers already use (subfinder, httpx, nmap, ffuf, nuclei) into a single MCP server so an LLM agent can plan and execute reconnaissance itself — passive subdomain/DNS/wayback discovery, active port scanning, WAF detection and origin-bypass checks, endpoint fuzzing, and nuclei scans. Structured JSON results carry scan tokens that let the agent chain one step's output into the next without re-typing targets.

A security testing tool that enables automated vulnerability detection including XSS and SQL injection, along with comprehensive browser interaction capabilities for web application penetration testing.

Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.

Comprehensive forensic analysis MCP server enabling AI agents to analyze files, Chromium and Firefox browser artifacts, with VirusTotal, DIE, Binwalk integrations.

A community security-research MCP server providing Browser Session and OIDC authentication for Okta workspaces, enabling read-only exploration of Okta organizations and user identity.

A self-hostable, vulnerable-by-design MCP server for learning how object-level authorization bugs (BOLA/IDOR) appear in multi-tenant tools.

Provides a Model Context Protocol server implementation that allows AI agents and other MCP clients to programmatically interact with DefectDojo, a vulnerability management tool, for managing findings, products, and engagements.

A Codex-style MCP server providing 126 tools to operate a Kali Linux machine from ChatGPT or any compatible MCP client, including shell execution, filesystem operations, Git, Docker, browser automation, and security tool wrappers.

Provides MCP clients like Claude with tools to query and manage security scans, CVEs, assets, findings, threat intel, and generate polished reports by acting as a lightweight adapter over the CVEasy backend API.

Enables an agent to probe a remote MCP endpoint with a few read-only, anonymous requests and get back a timestaped, evidence-grade verdict on whether its tool inventory is exposed without authentication, who can re-verify it themselves. Verdicts include unauthenticated-surface, authenticated-ok, and error classes, with no handshake forgery or exploit payloads.

A Model Context Protocol (MCP) server for integrating with StackHawk's security scanning platform. Helps developers set up StackHawk, run security scans, and triage findings to fix vulnerabilities — all from within an LLM-powered IDE or chat.

Enables coding agents to run security scans on repositories through a local stdio bridge to a hosted endpoint. Includes browser-based OAuth sign-in and local token storage.

Enables AI agents to perform pay-per-call security verification of wallets, tokens, contracts, dApps, agents, and more via a remote endpoint with no installation.

A TypeScript MCP server delivering a vendored 'dangerous skills' corpus and adversarial fixtures over MCP for security-research testing, supporting SEP-2640 skill delivery with archive-safety hardening.

Enables running Kali Linux security tools and commands in a containerized environment for semi-automated penetration testing, with background job management and out-of-band interaction detection.

It enables AI agents to connect to a live Chrome browser for automation and authorized security testing, including session-aware tab control, network capture and replay, DOM inspection, screenshots, and background workflows.

Enables AI-assisted penetration testing by connecting MCP clients to execute terminal commands on a Kali Linux machine, supporting tools like Nmap, Metasploit, and custom commands.

Enables MCP clients to drive IDA Pro through a stability-hardened server that hosts multiple headless idalib instances, with per-session isolation, configurable HTTP/stdio transports, and API-key authentication.

Enables a language model to inspect proxy history, run scoped scans and intruder jobs, and drive a proxied browser through Burp Suite for authorized security testing on test and staging environments. Scope, environment, mode, rate limits, refusals and secret redaction are enforced in gateway code with a tamper-evident audit log.

A cross-chain bridge security auditing toolkit that exposes tools for analyzing, fuzzing, and simulating bridge contracts via natural language, enabling users to detect vulnerabilities like centralization risks and replay attacks.

Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.

Gorgon Scout is a Windows web-application and API security scanner (DAST). This connector exposes it as MCP tools, so your AI assistant can record a target you are authorised to test, run the scan, stream findings, and produce a report. Capture needs no proxy or certificate setup, and it intercepts HTTP/1.1, HTTP/2, and HTTP/3 (QUIC). Works with the free Claude Desktop plan.

Enables auditing npm, Yarn, and pnpm lockfiles in local project directories or remote Git repositories to surface dependency vulnerabilities. Exposes a tool that supports severity thresholds, registry overrides, optional dev-dependency skipping, and text or JSON reports.

Enables an AI assistant to run nmap scans and host/service audits strictly against networks you are authorized to test, using a fixed set of safe, non-extensible tools instead of raw nmap flags, with results stored for history and diffing.

Exposes 18 typed tools that drive real static-analysis engines (Ghidra, apktool, WABT, TShark, evmole, Rizin) over a single MCP endpoint to decompile binaries, audit APKs, scan EVM contracts, inspect WebAssembly, firmware, SQLite, and pcap data. Every call returns signed, verifiable evidence with an evidence_id, provider identity, SHA-256 artifact digest, and explicit limitations for security research, malware analysis, forensics, and CTF work.

Enables AI agents to analyze memory dumps for forensic investigation, leveraging a fast Rust engine and full Volatility3 plugin coverage via the Model Context Protocol.

A proof-of-concept tool that integrates AI into security operations, allowing users to perform offensive security tasks like network scanning and reconnaissance through natural language commands to GitHub Copilot.