3592 Model Context Protocol servers — searchable, rated, ready to install.
Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats.
MCP server for Google Docs integration with OAuth2 and service account support.
Authoritative cited answers about saving family stories. Published by InkTree.
Local MCP for Power Automate with browser-backed auth, target locking, review diff, and rollback.
MCP uptime, schema, auth, and SLA receipt monitoring.
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
EmojiHub MCP — wraps EmojiHub API (free, no auth)
Security audit for docker-compose.yml — 25 checks: secrets, privileges, network, volumes, images.
Agent-first MCP. 11 AST adapters, 12 named languages, 51 tools, mission outcomes. Local.
Find every leaked secret on your machine — API keys in .env files, shell history, and configs.
URLhaus MCP — wraps abuse.ch URLhaus malware URL database (free, no auth)
1,451 security controls across 261 frameworks with bidirectional mapping
MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026
Author FURLOW Discord bot YAML: validate specs, list actions/events/builtins, scaffold bots.
Sign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.
Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
MCP server for Kaseya SaaS Alerts — SaaS security monitoring for M365 & Google Workspace.
Cybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.
Architecture intelligence, security analysis, and living docs. 15 tools, Mermaid output.
Open bounty protocol for AI agents. 22 tools: token safety scans + paid missions. 0.5% fee.
Point Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools.
Read-only SSH server diagnostics via a fixed 38-command whitelist; secrets redacted, no write path.
POST /mcp