"Assessing security risks of inputting sensitive material into a hosted MCP server" matching MCP servers:

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Provides sensitive word detection and filtering capabilities for LLMs, supporting multiple categories and real-time lexicon updates.

Enables browsing Material Design 3 documentation by listing top-level sections and retrieving page content as Markdown.

Detects Chinese sensitive/forbidden words across platforms like Xiaohongshu, Douyin, Kuaishou, and Bilibili, with risk levels and replacement suggestions.

A self-hosted Model Context Protocol server for Microsoft To Do. The key problem this solves: the Microsoft Graph API silently omits user-created lists on personal accounts (GET /me/todo/lists only returns well-known lists like "Flagged Emails"). This server works around it with a local SQLite registry that tracks every list you create, so your lists always show up.

CP server for RAD Security, providing AI-powered security insights for Kubernetes and cloud environments. This server provides tools for querying the Rad Security API and retrieving security findings, reports, runtime data and many more.

Enables querying Fathom video meetings: list, search, get transcripts, summaries, and action items.

An MCP server protected by Cloudflare Access as a self-hosted application, validating Access JWT and conditionally exposing tools based on user identity.

Enables AI assistants to deploy and manage static websites on EdgeOne Pages through a self-hosted MCP server. Supports one-click deployment, custom domain binding, and direct API access.

An MCP server that gives Claude and other AI agents the ability to audit any public URL's HTTP security headers. What it checks: * HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy * HTTPS enforcement and redirect chain depth * Presence of security.txt, robots.txt, sitemap.xml Payment model: * 0.05 USDC per scan, paid automatically on Base via the x402 proto

Enables AI agents to audit email and domain security (SPF, DKIM, DMARC, etc.) for any domain without requiring API keys.

MCP server for searching papers from top-tier and second-tier security conferences (S&P, USENIX Security, CCS, NDSS, ACSAC, RAID, ESORICS) using DBLP, with tools for keyword/author/year/conference search, listing conference papers, and getting statistics.

An MCP server that enables AI agents to perform comprehensive GitHub security audits across org settings, repositories, Actions workflows, secrets, supply chain, and access control using 39 tools and 45 checks.

Unified MCP server integrating NIST and OWASP security frameworks with live vulnerability data, enabling security searches, compliance mapping, threat modeling, and checklist generation.

Enables auditing a Supabase project's security beyond the dashboard's Security Advisor, checking anonymous access, RLS policies, and cross-tenant data leaks via read-only probes and a two-account test.

MCP server for integrating self-hosted Sentry with AI assistants, enabling project and issue listing, issue details with stack traces, and event retrieval.

MCP server for scanning smart contracts for security vulnerabilities. It detects issues like reentrancy, overflow, access control, and provides security scores with NEAR-specific recommendations.

MCP server for Appwrite security audits that scans permissions and provides structured fix proposals, with active live leak confirmation via anonymous fetch.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.

Enables integration with Beagle Security API for managing security testing projects, applications, domain verification, and automated penetration tests. Provides 18 tools for creating, monitoring, and retrieving results from security assessments.