"An overview or explanation of 思维链 (Chain of Thought)" matching MCP servers:

Enables auditing cross-chain bridge token reserve invariants and monitoring outflow spikes for LayerZero and Wormhole bridges, helping detect reserve anomalies and potential vulnerabilities.

An offensive security dataset generator that creates high-quality, multi-turn penetration testing conversation datasets for fine-tuning security-focused LLMs. It enables users to generate realistic pentesting workflows featuring chain-of-thought reasoning, tool outputs, and over 45 diverse attack scenarios.

Enables agents to inspect web pages for Cloudflare Turnstile challenges without an API key, and clear Turnstile or WAF challenges using a SolveGate API key.

An MCP server that scans local codebases for quantum-vulnerable cryptography (secp256k1, Ed25519, RSA, etc.) and CI signing commands, classifying each finding as quantum-broken, post-quantum, or neither. It runs entirely locally with no network calls, providing a deterministic inventory for AI agents.

Enables scanning of Claude Code skills, plugins, or MCP servers for malware before installation via static analysis.

Enables Android APK reverse engineering and Flutter runtime injection through a six-step pipeline of decompile, analyze, synthesize, inject, patch, and repackage. Provides MCP tools for authorized security research and penetration testing.

Enables AI agents to access VirusTotal intelligence through MCP, supporting file, URL, domain, and IP lookups, plus analysis, via remote HTTP or local stdio.

Connects AI assistants to Solodit's 49,000+ blockchain vulnerability database, enabling search, browse, and lookup of audit findings directly from your AI workflow.

Provides access to Atomic Red Team tests, enabling search, validation, and execution of atomic tests via natural language.

An MCP server that lets an AI agent probe a live URL and confirm whether sensitive files (e.g., .git, .env, source maps) are genuinely served by fetching and validating the content, avoiding false positives.

Free deterministic security scan of a public git repository (GitHub, GitLab, Codeberg, Bitbucket): vulnerable dependencies via OSV.dev, secret patterns, and config lint, returned as structured JSON. Tools: scan_repository(url), audit_pricing(). Runs locally over stdio (python3 web/mcp_stdio.py or the Dockerfile) and is also hosted at https://project-feldspar.com/mcp. MIT licence, stdlib-only. Buil

Captures formatted screenshots of Caido Replay request/response pairs by driving the Screenshot Mode plugin via Chrome DevTools Protocol.

Enables passive security scanning of HAR files from QA test automation to detect missing security headers, insecure cookies, CORS misconfigurations, and leaked secrets, without making any live requests.

GhostHunt is an MCP server that scans your development machine for API keys, tokens, and credentials hiding in places you forgot to check.

Self-hosted MCP engine for private code reviews, providing deterministic static analysis and AST-level search over diffs, with findings passed to a review agent of your choice.

Connects an AI assistant to an already-running mitmweb session so it can read, search, diff, replay, and generate code from the same network flows shown in the UI.

Static security scanner for AI-generated (vibe-coded) Supabase and Next.js apps. Runs as an MCP server so an LLM can scan, explain findings, and produce fixes while it writes code, all locally and offline.

An MCP server that audits zero-knowledge circuits (Circom, Noir, Halo2) for soundness and constraint bugs, powered by the Cysic Minimax model.

Enables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks.

Enables AI agents to run reconnaissance tasks such as DNS, WHOIS, certificate transparency, TLS certificate, HTTP header, and limited port checks against explicitly authorized domains and IPs. Scope permissions, deny rules, default-deny resolution pinning, rate budgets, and append-only audit logging are all enforced inside the server so an out-of-scope request cannot be expressed.