13 #secrets MCP Servers & Clients

envmcp

griffithsbs

A lightweight way to use environment variables in your Cursor MCP server definitions.

MCP server giving AI agents full SSH access with secret-safe environment variable injection. Supports persistent sessions, structured command execution, SFTP file transfer, port forwarding, and automatic output redaction that prevents secrets from reaching the LLM.

Conduit

tsouth89

Conduit is a local-first gateway that puts every MCP server behind one endpoint shared by all your AI coding tools (Claude, Cursor, VS Code, Codex, and more). Set up and authenticate each server once, then connect every client to Conduit instead of re-adding servers everywhere. K

🌍 envmcp: Simplifying Environment Variables for Cursor MCP Servers

dfhgnh43terg

A lightweight way to use environment variables in your Cursor MCP server definitions.

Find every leaked secret on your machine. Scans .env files, shell history, and config directories for API keys, tokens, and credentials. 35+ patterns including AWS, Stripe, GitHub, OpenAI, and more. Everything runs locally. Zero network calls.

Haldir

ExposureGuard

The guardian layer for AI agents. Scoped sessions with spend limits (Gate), AES-encrypted secrets (Vault), immutable audit trail with anomaly detection (Watch), and proxy mode that intercepts every MCP tool call for policy enforcement. Human-in-the-loop approvals, webhooks, 10 MC

Share encrypted, self-destructing secrets directly from Claude, Cursor, or Windsurf. Zero-knowledge E2E encryption. Agent-blind input sources (env:, file:, dotenv:) — secrets never pass through LLM context.

Store and retrieve API keys and secrets locally for Claude Code. No cloud services, no .env files scattered across projects. Secrets are stored in a SQLite database on your machine and accessed via MCP tools. Supports add, get, list, search, update, and delete operations with cat

Zfuzz

Zfuzz-dev

Real security scanners for AI coding agents: SAST (441 rules), secret detection (419+ patterns), dependency CVEs, MCP/skill vetting, MITRE ATT&CK. Real scanners,

Provides a bridge for scripts and AI agents to interact with a self-hosted Vaultwarden instance.

Deaddrop

jerrywrongalot-byte

MCP server: AI agents share self-destructing one-time secrets via DeadDrop - zero-knowledge, paid per call in USDC over x402 on Base

Burn-after-read encrypted notes for AI agents. Share secrets with users without them appearing in chat history — create a one-time URL, send it, they read it once and it's gone. AES-256-GCM E2E encrypted, decryption key never sent to any server.

Cycode

cycodehq

Boost security in your dev lifecycle via SAST, SCA, Secrets & IaC scanning