3475 Model Context Protocol servers — searchable, rated, ready to install.
Lint OpenAPI 3.x documents for missing security, responses, descriptions and versioning.
Sourced, scored comparisons of crypto exchanges, wallets, savings accounts and brokerages.
Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.
Public website health scan, AI-crawler and structured-data readiness, and a local presence score.
Audit apps against App Store, Google Play and Google OAuth review rules; get the required docs.
Search public Threads posts by keyword for AI agents: text, author, likes, replies, reposts.
MCP server demo — tickets, schema discovery, auth, and PII gating. stdio + HTTP.
Read-only AI impact metrics with search, methodology and cited sources. No authentication required.
Deterministic execution boundary and reference MCP sidecar for Arcstone Security Stack
Answer security questionnaires and RFPs from your AI knowledge base.
Security incidents across Nigeria, such as kidnapping and banditry, with sources and confidence.
Your personal career coach. Scanning jobs for you, daily.
Inspect authorized website tracking, compare consent observations, and get remediation guidance.
DeFi vault judgment for agents: 16-factor Atlas Score, route survival, blowup alerts. Read-only.
Configure, price, render and order a made-to-order B.R.M watch (French manufacture). No auth.
Generate visual analytical reports from verified outlines. Account and OAuth required.
Uganda URSB company search by name and BRN, with director, secretary and shareholder lookup.
Read-only BoomTax tools for filings, forms, payers, and e-file status through OAuth.
Privacy-first cookieless web analytics with agent one-prompt setup via remote MCP OAuth.
Dutch address data for AI assistants: BAG building facts, energy labels, reviewed crime signals.
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
Offline full-text search over the HackTricks security wiki, synced every 3 days.
Let AI agents use secrets without seeing them: masked output, every use approved in JFSecure.
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
POST /mcp