"Security Tools for AI Websites" matching MCP servers:

Free Industry 4.0 / IIoT tools, no API key or account: lint MQTT Sparkplug B topics, check a Unified Namespace (UNS) for naming and hierarchy problems, and run an industrial AI-readiness diagnostic for manufacturing digital transformation and smart-factory projects. Works in Claude Code, Codex and any MCP client.

50 tools and 400 functions for working with Excel/.xlsx spreadsheets — read/write, recalculate formulas, diff, repair broken references, and audit. Built for AI agents.

Enables agents to classify AI systems, scope relevant risks and controls, investigate evidence, propose remediations, and explain results through read-only tools, reference resources, and prompts.

Enables scanning OpenAPI specifications for security gaps and generating security test checklists for APIs.

Autonomous AppSec & DAST code and website security scanner across 12 security domains (260+ controls) with 3-Layer Triage.

Provides MSP support tools (ticket search, draft response, KB search, update) with a deterministic security guardrail that refuses to draft responses for security tickets based on content scanning, even if mislabeled.

Standalone MCP server and CLI for generating images via ChatGPT backend, with reliable exact file paths and multi-account login support.

Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.

Enables AI agents to check a list of websites by running an Apify Actor through one tool, returning per-site tech stack, on-page SEO issues and score, robots.txt rules for AI crawlers, sitemap, llms.txt presence, and an AI-readiness score. Supports local stdio operation with an Apify token for tool calls.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

SOC2 Compliance AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Zero-dependency MCP server for social media dimensions & first-party safe areas (Reels, TikTok, YouTube Shorts), encoder-safe aspect ratios, video bitrate math, SRT/VTT/ASS subtitle conversion, and BPM delay tables.

Educational tools agent by Birkan Yavuz — an A2A + MCP server for classroom tools, with creator attribution in every result. It offers a catalog of 24 real classroom activities, including math visualizers and reading and sight-word tools.

Pay-per-call USDC payment proxy for AI agents. Issue scoped Pay Tokens with hard spending caps and auto-journal every charge to freee / Money Forward / QuickBooks.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Enables deterministic calculations for AI API and subscription costs, meeting time zones, recurring schedules, and cron next-run previews, returning normalized inputs, units, assumptions, dated sources, and links to results.

Enables AI agents to access Cloudflare Workers AI for serverless LLM chat completions, text embeddings, and image generation via MCP tools.

Release gate agents call before they tell users a public website is ready to ship. Scans public websites across security, SEO, accessibility, legal compliance, and sustainability.

Integrates the Metis FCA Handbook AI Harness into Claude Desktop to analyze FCA Handbook applicability for financial products, services, or firms, returning structured compliance reasoning with verbatim citations.

An MCP server that reads a file's embedded C2PA Content Credential to report whether it declares AI generation or a real-world capture, and checks whether that declaration's signature still verifies against the file's current bytes.

Official MCP server for the EU AI Act. Search and access Articles, Recitals, Annexes, timelines, obligations, prohibited practices, GPAI requirements, conformity assessments, and compliance information across all 24 official EU languages.

Enables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.

Records privacy-preserving receipts for AI-assisted tasks and enables optional onchain reward claiming via AIPOU tokens. Integrates with MCP-compatible clients like Claude and Cursor.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

Three deterministic MCP tools that score text for AI-writing tells (em-dash density, hedge words, tricolons, boilerplate openers) and grade landing-page copy. No LLM, no network calls, no API key — same input always yields the same score. Published on the official MCP registry as io.github.parweb/ai-slop-checker.

Enables searching and browsing the entire F5 AI Security documentation using TF-IDF search and section reader tools.

MyChart MCP Server

Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.

MCP server for jar.tools' JAR security scanner. Enables AI agents to scan local .jar, .zip, or .class files for supply-chain risk without opening a browser.