# mild run

> mild run — mild-run-mild-run-mcp. Use this tool when you need to secure and control AI agent interactions with sensitive services like Stripe, Gmail, and Slack. It intercepts actions and sends notifications for approval or blocking, ensuring agents never hold credentials. This tool solves security and authorization problems, providing a safe interface for AI agent operation.

Canonical page: https://skillsregistry.net/skills/mild-run-mild-run-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mild-run-mild-run-mcp

## Description

Your AI agent can't touch Stripe, Gmail, Slack or more, without your tap. mild.run intercepts every sensitive action and sends you a notification to approve or block — before anything executes.    Agent never holds credentials.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ag2q8n56tg)
- **Repository:** <https://github.com/mild-run/mild-run-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mild-run-mild-run-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mild-run-mild-run-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mild-run-mild-run-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt