Security

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

Security scanner for MCP server configurations. Finds risky tools, vulnerable packages, and suspicious servers across Claude Desktop, Cursor, VS Code, and more.

120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).

Find secrets leaking through your AI coding agent's session history. Zero network calls in the scan path, zero dependencies.

PreMan CLI and stdio proxy for PreMan's hosted MCP server

MCP server and framework adapters for Corsair. Expose 200+ integrations to any agent framework (Mastra, LangChain, LlamaIndex, OpenAI, Vercel AI, Claude) as tools.

DoI score lookup, vouch event builder, and offline schnorr verify for AI agents.

Papercliped — connect Claude, ChatGPT and any MCP app to your Paperclip: control agents, sync, report. MCP server + hosted multi-tenant OAuth bridge + public stats API.

The Bridge CLI: set up and manage sign-in, roles, plans, feature flags and API tokens from your terminal or AI coding agent.

Finds authorization holes in Next.js + Supabase apps and live Supabase databases. No API key.

CLI and MCP server for LinkedIn — 43 commands for profiles, posts, messaging, connections, search, feed, and more. Cookie session auth, AI agent native.

AEAP Composition Boundary reference implementation for MCP servers. Attaches the Runtime Decision Point above an MCP tool-invocation boundary. Node sibling of aiyoplane-mcp-authz on PyPI.

Self-hosted MCP gateway: one streamable-HTTP endpoint federating many MCP servers with namespaced tools, per-tool toggles, roles, and secure upstream credential injection

Auth, email, journeys, surveys, webhooks, and analytics for SaaS in one project, one API key.

Earn-native MCP server for the LI.FI Earn API: 12 tools for vault discovery, risk scoring, allocation, and deposit quoting

Charge AI agents per-call without accounts. PoW solve = free tier, Lightning = paid tier.

Admission control for HTTP MCP servers: only AER-attested agents reach your tools; rogue agents get a JSON-RPC deny.

Blockchain-backed memory and code storage for Claude Code. Save AI conversations and source code permanently on BSV.

Was this document edited, did its redactions hold, is it safe for a model to read — Tamperlens API.

Interactive LeetCode MCP server with authorization and solution submission capabilities