"Ways to Improve Thinking Skills" matching MCP servers:

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

SkillTotal is a local stdio MCP server that lets an agent check a component before installing it. It statically analyzes MCP servers, agent skills, npm/PyPI packages and repos for supply-chain risks, dangerous capabilities (shell, filesystem, network, credentials), prompt-injection surfaces like tool poisoning, and exfiltration paths. Each finding cites file, line and snippet.

Unified MCP server that gives AI agents security tools to audit MCP configs, redact secrets/PII, vet skills, check dependencies, and scan networks.

Local-first security scanner for AI agent skills, plugins, hooks and MCP servers. Read-only, offline tools to scan a skill or MCP server before installing it, audit the installed setup and review proxy pins.

Enables AI assistants to scan websites, public repositories, and OpenClaw/CLAW skills for security vulnerabilities, including local skill-package analysis before installation, cloud scans, and remediation guidance.

Security gate that scans MCP servers and Claude Code Skills for vulnerabilities before execution.

A security gate MCP server that audits agent extensions (skills, MCP servers, tools) by scanning for risks, adversarial analysis, and sandbox execution, returning a trust verdict of allow, quarantine, or block.

Enables AI agents and external tools to perform reverse engineering on compiled binaries through IDA, including decompilation, disassembly, cross-references, type management, patching, signature generation, and dynamic debugging.

Scans remote MCP endpoints, manifests, and agent skills for security threats, providing deterministic scores, verdicts, and signed reports to verify agent infrastructure before trust or payments.

Enables real-time injection fuzzing, exfiltration canary detection, least-privilege tool sandboxing, and cryptographic audit proofs for untrusted prompts, RAG context, and agent actions over MCP.

Enables real-time injection fuzzing and canary-based exfiltration detection over untrusted prompts, RAG context, and agent actions, with entropy analysis, outbound channel interception, least-privilege sandboxing, and cryptographic audit proofs.

Enables agents to generate tamper-evident SHA-256 Merkle audit trails, produce logarithmic inclusion proofs, and verify integrity through a STDIO MCP interface.

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.

Security scanning for AI agent skills, MCP servers, and agent prompts, returning signed trust scores and detailed findings.

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.

Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.

Enables authorized penetration testers to run reconnaissance, web fuzzing, vulnerability scanning, brute-force/password cracking, traffic capture, privilege-escalation audits, wordlist generation, and client-report workflows over stdio, HTTP, or SSE with optional bearer/OIDC authentication.

Enables users to scan AI agent skills and configuration files for hidden Unicode instructions, prompt injection, download-and-execute payloads, exfiltration patterns, and overly broad permissions before installation. It provides static audit tools for skill files, agent configs, and revealing hidden text without executing or fetching the input.

Enables professional penetration testers to orchestrate reconnaissance, web/content scanning, brute-force checks, traffic capture, privilege-escalation auditing, wordlist generation, and client reporting through MCP transports with optional bearer/OIDC authentication.

Provides DNS and network-reconnaissance tools that let agents run lookups for records, reverse DNS, ping, passive subdomain discovery, shared nameservers, geolocation, reverse IP, ASN, HTTP headers, subnet arithmetic and page links, plus key-gated WHOIS, MTR and traceroute. Responses are parsed into structured JSON with verbatim raw text, and it runs either through a hosted gateway or as a local stdio server.

This MCP server enables real-time injection fuzzing, exfiltration canary detection, least-privilege tool sandboxing, and cryptographic Merkle audit proofs for agent prompts, RAG context, and actions. It provides tamper-evident SHA-256 tree generation, logarithmic inclusion proofs, and verifiable integrity checks through MCP.

Connects MCP clients to a Kali Linux terminal for executing security tools and commands, enabling AI-assisted penetration testing and CTF solving.

Enables authorized penetration testers to run reconnaissance, enumeration, vulnerability scanning, brute-force checks, traffic capture, and exploitation workflows via MCP tools, with STDIO/HTTP/SSE transport support. It also manages engagement records and generates client reports.

Enables users to score credential strength using NIST-style bit entropy and keyspace calculations, estimate GPU brute-force cracking timelines, audit cross-account password reuse blast radius, and perform k-anonymity SHA-256 prefix privacy checks without exposing secrets.

Enables autonomous AI agents and penetration testers to conduct authorized security audits with persistent cross-session memory, zero-trust secret scrubbing, dynamic OWASP/ASVS checklists, and hallucination-free exploit PoC generation from captured traffic.

Enables AI assistants to drive OWASP ZAP for authorized penetration testing and bug-bounty workflows, including authenticated scans and vulnerability triage through 67 curated safety-gated tools.

A stateful debugging and binary research system for LLM agents, integrating GDB + pwndbg with MCP for deterministic exploit workflows and multi-session support.

Enables real-time injection fuzzing, exfiltration canary detection, least-privilege tool sandboxing, and cryptographic audit proofs through the Model Context Protocol.

Enables professional penetration testers to run reconnaissance, exploitation, brute-force, traffic capture, and reporting workflows through stdio, HTTP, and SSE transports with auth and engagement record management.