3236 Model Context Protocol servers — searchable, rated, ready to install.
Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
Auth infrastructure for coding agents. User pools, secrets vault, token management. As easy as git.
Authenticated MCP Agent (Bcrypt)
Authenticated LLM Traced Agent
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Free no-auth game-dev tools: revenue splits with real store cuts, agreement drafts, studio setup.
Odoo ERP for AI agents: hosted OAuth endpoint, gated writes, one endpoint for every instance.
Local agent spend-policy checks. No funds, keys, payment authority, or network access.
Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.
Browse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.
Korean SMB marketing: browse, pay by card link, track orders. No login to start; OAuth to link.
QuickBooks Online MCP server for invoices, customers, and payments. OAuth 2.1 + PKCE, stdio/HTTP.
Generate, edit and track dynamic (editable) QR codes with scan analytics. Hosted MCP and REST API.
On-device PDF, resume and CSV tools. Files never leave your machine. Refuses rather than guessing.
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
Authenticated LLM MCP Agent
Persistent memory for AI assistants — one shared, OAuth-secured vault for every MCP client.
Look up the technology stack behind any domain, and the company running it.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Live vault metrics and docs for SukukFi, Islamic trade finance on Berachain. Read-only.
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
POST /mcp