MCPLow riskUnclaimed

safeagent

Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.

azender1azender1/safeagent★ 7Updated Jun 17, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.azender1/safeagent",
  "description": "Exactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.",
  "repository": {
    "url": "https://github.com/azender1/SafeAgent",
    "source": "github"
  },
  "version": "0.1.22",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "safeagent-exec-guard",
      "version": "0.1.22",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:safeagent-exec-guard@0.1.22
Runs install scripts—None
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. #10.1.22latestOct 7, 2026