"A task involving critical or creative thinking" matching MCP servers:

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.

A read-only MCP server for the Qualys PCI Merchant API that lets LLM assistants answer questions about PCI compliance posture, such as which hosts are failing PCI or listing high findings.

Connects MCP clients to pre-submission review that argues against a draft bug-bounty report or smart-contract finding the way a triager would, tying every claim to a supplied file and line and returning a submit, rewrite-then-submit, prove-first, hold-duplicate or drop verdict. Exposes tools to list review profiles, prepare reviews for the agent's own model, build hash-verified review packets, and — with a connection token — run hosted profiles on your own provider key.

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 agents and CI pipelines to audit MCP servers and agent tool-chains by statically scanning repositories, local checkouts, tools/list exports, or live endpoints for risks such as destructive actions without confirmation, mismatched safety annotations, injection surfaces, credential or PII exposure, and unguarded command, path, or URL sinks. All checks are read-only and never execute the scanned code or call tools/call.

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

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.

A read-only MCP server that lets an agent browse the HackerOne Hacker API using an authenticated hacker account, exposing programs, policies, scope, reports, and payments. It cannot create, update, or submit reports.

Enables AI assistants to search TryHackMe rooms and extract room overviews, task instructions, commands, and questions as clean Markdown for training and reference. Supports session-cookie authentication for subscriber content and includes curated foundational cybersecurity and Linux learning tracks.

Enables AI coding assistants to run pre-publish security and code-quality scans across 17 categories, generate a 0–100 security score and Markdown report, quickly check critical vulnerabilities, and receive fix/refactor suggestions by finding ID.

Enables security inspection of MCP tool metadata by analyzing tool names, descriptions, and input schemas, and returning SAFE, REVIEW, or HIGH RISK verdicts through the analyze_tools tool.

Enables AI coding assistants to inspect ELF, PE, and Mach-O binaries for hardening mitigations and high-risk symbols, and to triage source or decompiled code against MITRE CWE patterns through MCP tools.

Enables AI agents and developers to audit any URL or domain for seven critical OWASP HTTP security headers, returning an A+ to F grade plus actionable Nginx, Apache, Caddy, and Cloudflare remediation snippets. It also probes /.well-known/security.txt and /security.txt to surface responsible vulnerability disclosure contacts, bug bounty scopes, and PGP keys.

A Model Context Protocol (MCP) server for Kerberos abuse operations using Rubeus on Windows or Impacket on Linux/macOS.

Talk to your Flipper Zero from Claude Code — or any MCP client. Storage, app deployment, screen capture, button automation, JavaScript execution on the device, and honest answers about what is nearby.

A security scanner for AI coding agents and autonomous assistants that scans code for vulnerabilities, detects hallucinated packages, blocks prompt injection, and provides LLM-powered semantic code review via MCP or CLI.

A security research MCP server for testing tool call safety with deterministic policies like allowlists, path boundary enforcement, SSRF prevention, output redaction, and prompt injection detection, without requiring external LLMs or API keys.

Enables coding assistants to sign in to a user's account, scan source code with static analysis, and review findings through a shared chat thread from Claude Code, Codex, or VS Code.

Enables generating falsifiable fleet hypotheses, compiling them into minimal bounded probe plans with control cohorts, and evaluating observations to return supported, refuted, or inconclusive verdicts.

A radare2 MCP server for binary analysis and reverse engineering, enabling AI agents to interact with radare2 through natural language or structured commands for tasks like static analysis, debugging, and patching.

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.

Integrates Snyk security scanning with MCP clients like Claude Code, enabling listing of projects, querying issues by severity, and filtering by project or scope.

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 MCP clients such as Cursor, Claude Desktop, and Claude Code to run deterministic static-analysis tools for scanning projects, listing entry points and reachable sinks, tracing taint paths, explaining findings, and checking sanitizers without API keys or network access.

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 launching a fixed clean or poisoned MCP test fixture over stdio so agents can be evaluated for task utility and resistance to malicious instructions embedded in tool results.

Enables triggering GuardBee security scans via natural language, checking scan status, filtering findings by severity or ID, and obtaining AI-assisted remediation guidance.

Enables comprehensive TLS security audits for any domain, including certificate validity, expiry warnings, cipher suite weaknesses, deprecated protocols, and HSTS checks. Supports single and bulk domain inspection via MCP tools or a CLI for CI/CD integration.

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.