# Impri

> Impri — sekera-radim-impri. Use this tool when you need to ensure AI agents' actions are reviewed and approved by humans before execution, solving issues of accountability and safety in automated decision-making. Impri provides a human-in-the-loop approval inbox that takes in proposed actions from AI agents and outputs approved, rejected, or edited actions through web, mobile, or messaging platforms. It is ideal for use cases requiring strict control and audit trails, such as sensitive email sending or command execution.

Canonical page: https://skillsregistry.net/skills/sekera-radim-impri  
JSON: https://api.skillsregistry.net/v1/skills/sekera-radim-impri

## Description

Human-in-the-loop approval inbox for AI agents: an agent proposes an action (send email, post comment, run a command), a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only runs on approval. Full audit trail, self-hostable (MIT).

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/n7gsuu5h9z)
- **Repository:** <https://github.com/sekera-radim/impri>

## 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": "sekera-radim-impri"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sekera-radim-impri` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sekera-radim-impri/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