sekera-radim

[](https://glama.ai/mcp/servers/sekera-radim/impri) 🎖️ 📇 ☁️ 🏠 - Human-in-the-loop approval inbox for AI agents. An agent submits a proposed action (send email, post comment, run a command) via `impri_push_action`, a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only proceeds on an approved decision. The gate is a data dependency, not a pro

[](https://glama.ai/mcp/servers/sekera-radim/briefgate-mcp) 📇 ☁️ 🏠 - Client intake for AI agents: request files, texts and credentials from a client, chase automatically, pull the results when complete.

Human approval inbox for AI agents. Before your agent does something that matters (a refund, an outbound email, a deploy, a publish), it proposes the action with a preview via impri_push_action. A human approves, edits or rejects it from the web inbox, Slack, Telegram, Discord, email or a phone, and the agent waits for the decision with impri_await_decision before executing. Fail-closed by default, every decision is audited. Connect with your Impri API key (Bearer im_...); the hosted tier is fre

Client intake for AI agents. When a task is blocked on input only an outside person can give (a client's logo, copy, photos, structured answers or logins), the agent declares the items with define_intake. BriefGate emails that person one portal link that needs no account, reminds them on a schedule until everything is in, validates each answer against typed items, and the agent pulls the results back with get_intake_results. Credentials are encrypted and revealed once. Sign in with OAuth (free p