Secure MCP Server

Encrypted secrets and credential management for agents

Local serverstdio

What is the Secure MCP server?

Encrypted secrets and credential management for agents. That is what the secure mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

MCP server for agent-native secrets management. 24,008 secrets have been found in MCP config files on public GitHub. This server solves that.

The tools it exposes

The server publishes 6 tools. What each one is for:

  • store_secret — The store_secret tool exposed by this server
  • get_agent_token — Issue a short-lived, scoped token. The agent receives an opaque token ID, never the raw secret
  • rotate_secrets — Rotate all secrets for a service. Old tokens are invalidated
  • audit_secret_access — The audit_secret_access tool exposed by this server
  • scan_config_for_leaks — Scan config text for exposed secrets. Detects AWS keys, GitHub tokens, OpenAI/Anthropic keys, Slack tokens, Stripe keys, private key blocks, bearer
  • inject_secret_to_request — Return a request with the secret injected server-side. The agent provides a template with {{SECRET}} placeholder and a valid token ID

Getting it running

Installation goes through your MCP client rather than a global install: point it at secure-vault-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Secure's toolset — store_secret, get_agent_token, rotate_secrets and 3 more — is a fair guide to whether it matches your workflow. It is maintained by mdfifty50-boop; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
store_secretThe store_secret tool exposed by this server.
get_agent_tokenIssue a short-lived, scoped token. The agent receives an opaque token ID, never the raw secret.
rotate_secretsRotate all secrets for a service. Old tokens are invalidated.
audit_secret_accessThe audit_secret_access tool exposed by this server.
scan_config_for_leaksScan config text for exposed secrets. Detects AWS keys, GitHub tokens, OpenAI/Anthropic keys, Slack tokens, Stripe keys, private key blocks, bearer tokens, and generic credentials using 12 regex patterns.
inject_secret_to_requestReturn a request with the secret injected server-side. The agent provides a template with {{SECRET}} placeholder and a valid token ID.

How to install the Secure MCP server

{
  "mcpServers": {
    "secure-vault": {
      "command": "npx",
      "args": ["-y", "secure-vault-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Secure to store secret.
  • Use Secure to get agent token.
  • Use Secure to rotate secrets.

Frequently asked questions

It connects Secure to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (store_secret, get_agent_token, rotate_secrets, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Secure directly.