3334 Model Context Protocol servers — searchable, rated, ready to install.
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Web accessibility scanning (WCAG 2.2 AA + KWCAG 2.2) with Korean remediation guides
Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.
Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
International real-estate search and buyer workflows for AI agents via MCP and OAuth 2.1.
Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.
Semantic search and pattern discovery for Obsidian and markdown vaults.
Authenticated LLM Traced Agent
Full-CRUD server for AEP, Journey Optimizer and CJA. 61 tools from one OAuth credential.
Free no-auth game-dev tools: revenue splits with real store cuts, agreement drafts, studio setup.
Browse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.
Read devices, users, keys, ACLs and DNS for a tailnet; manage devices, routes and auth keys.
OAuth LangChain OpenAI Agent
Korean SMB marketing: browse, pay by card link, track orders. No login to start; OAuth to link.
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
QuickBooks Online MCP server for invoices, customers, and payments. OAuth 2.1 + PKCE, stdio/HTTP.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Generate, edit and track dynamic (editable) QR codes with scan analytics. Hosted MCP and REST API.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Manage your RoyalTea game studio: tasks, milestones, team, and royalty data. 77 tools, OAuth 2.1.
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
POST /mcp