MCPLow riskUnclaimed

sealkeep

Let AI agents use secrets without seeing them: inject into a command, redact the output.

munhqmunhq/sealkeepUpdated Oct 9, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.munhq/sealkeep",
  "description": "Let AI agents use secrets without seeing them: inject into a command, redact the output.",
  "title": "sealkeep",
  "repository": {
    "url": "https://github.com/munhq/sealkeep",
    "source": "github"
  },
  "version": "0.3.0",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@munhq/sealkeep",
      "version": "0.3.0",
      "runtimeHint": "npx",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Path of the config file (stores, aliases, guard rules). Default: the config folder of the OS, for example ~/.config/sealkeep/config.toml. With no file, sealkeep uses the OS keyring.",
          "format": "string",
          "name": "SEALKEEP_CONFIG"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@munhq/sealkeep@0.3.0
Runs install scripts—npm:@munhq/sealkeep
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.3.0latestOct 9, 2026