Overview
Connect an agent to Deliverd: ask a person or publish a report from the SDKs, the REST API, the MCP server or the CLI, and choose between them.
Deliverd is the human layer for AI agents. An agent that needs a person — an approval, a review, an answer, a decision — asks through Deliverd and carries on when they respond. An agent that has made something publishes it to a secure address behind your organisation's sign-in. These pages are for the people who connect agents; the guide is for the people who answer them and run Deliverd.
The whole integration
import { deliverd } from "@deliverd/sdk";
const decision = await deliverd.approve({
title: "Deploy to production"
});
if (decision.approved) await deploy();What is not in that sample: the approval page, the email and the reminders, sign-in, who is allowed to decide, the audit trail, and the screen a person decides on. None of it is yours to build.
What you can build
- Ask before acting
- An agent about to spend money, deploy or contact a customer asks named people to approve it, and acts on what they approved. See Approvals.
- Ask the policy first
- An agent declares a registered action, and rules your organisation wrote allow it, refuse it or send it to a person. See The gate.
- Ask for judgement or facts
- Put a draft in front of reviewers, or ask people typed questions and get the answers back as data.
- Keep the record
- Tie a job's requests together in a flow and export who decided what, and when, as an evidence pack.
- Publish
- Put a report, dashboard or prototype at a persistent address, with versions, comments and live data. See Publishing reports.
Choose how to connect
| Use | When | Credential |
|---|---|---|
| SDKs | You write the agent, in TypeScript or Python. The waiting, retries and polling are done for you. | An API key |
| MCP server | The agent runs in Claude Code, Codex, Cursor, ChatGPT or another MCP client, and you write no code. | OAuth, approved in a browser |
| CLI | A terminal, a shell script or a CI job: publish on every build, or block a deploy until a person approves. | deliverd login, or a token in CI |
| REST API | Any other language or platform. Everything the others do is here. | An API key or OAuth token |
They are one service underneath: the same scopes, the same refusals, the same audit trail. Mixing them is normal — an agent that asks through MCP can be governed by a policy pushed from the CLI.
Install
TypeScript SDK
npm install @deliverd/sdk
Python SDK
pip install deliverd
claude mcp add --transport http deliverd https://deliverd.dev/api/mcp
Every AI tool on this machine, via the CLI
npx deliverd setup
The approval skill
npx skills add deliverd-dev/deliverd-skills --skill approval