delvry/

Agents need context — Delvry collects it. Your agent generates a short survey, sends it to the people who actually know, and gets structured answers back. No survey-writing UI for you. No login wall for them. Just a typed payload your agent can act on.

Or programmatically — see below.

$ curl -X POST https://delvry.ai/v1/accounts/signup     -H "content-type: application/json"     -d '{"email":"agent@example.com","account_name":"My project"}'

{ "account_id": "...", "first_api_key": "delvry_sk_...", "password_generated": true }

#Overview

Delvry is a survey backend designed for one specific user: an LLM agent that needs to ask a human a question and get a structured answer. The agent calls delvry.create_survey(), Delvry handles delivery, validation, branching, autosave, and the JSON shape of the response.

Three surfaces: /app (operator dashboard, for the human who owns the API key), /r/<jwt> (the recipient form, mobile-first), and the API (which is the only thing your agent talks to).

#How it works

  ┌────────┐    create     ┌────────┐    invite     ┌──────────┐
  │ AGENT  │►───────────► │ DELVRY  │►───────────► │ RECIPIENT│
  └────────┘               └────────┘               └──────────┘
       ▲                       │                          │
       │       answers         │       submit             │
       └───────────────────────└──────────────────────┘

  1. agent emits a survey DSL (9 question types · branching · validation)
  2. Delvry mints recipient JWTs and a public link
  3. recipient fills out the form (autosaved every 1s)
  4. agent fetches /responses or subscribes to webhook
  5. agent acts on the typed result

#Install

One paste, any Claude. The MCP server bootstraps its own API key on the agent's first delvry_signup call — no manual key-swap.

$ claude mcp add delvry -- npx -y @delvry/mcp

{
  "mcpServers": {
    "delvry": {
      "command": "npx",
      "args": ["-y", "@delvry/mcp"]
    }
  }
}

$ https://delvry.ai/mcp

$ mkdir -p .claude/skills/delvry && \
    curl -fsSL https://delvry.ai/skill.md > .claude/skills/delvry/SKILL.md

# install + bootstrap
$ npm i -g @delvry/cli
$ delvry signup
> ✓ Account created. account_id=...
> ✓ API key saved to ~/.delvry/config.json (chmod 0600)

# non-interactive (CI)
$ delvry signup --email agent@example.com \
    --account-name "My project" --yes

$ delvry surveys list

$ curl -X POST https://delvry.ai/v1/accounts/signup \
    -H "content-type: application/json" \
    -d '{"email":"agent@example.com","account_name":"My project"}'

{ "first_api_key": "delvry_sk_...", ... }

$ curl -X POST https://delvry.ai/v1/surveys \
    -H "Authorization: Bearer $DELVRY_API_KEY" \
    -H "content-type: application/json" \
    -d @retro.json

Agents: machine-readable install at /llms.txt.

#Survey schema

Nine question types: short_text, long_text, single_choice, multi_choice, number, yes_no, scale, ranking, date. Plus boolean toggles, Likert scales, click-to-rank, and date inputs. Branching via show_if. Pages auto-skip when every question is hidden. Required fields, min/max, default values, and per-question validation are all declared in the DSL.

{
  "version": "1",
  "title": "Q1 retro",
  "pages": [
    { "questions": [
      {
        "id": "role",
        "type": "single_choice",
        "prompt": "What's your role?",
        "required": true,
        "options": ["Eng", "Design", "PM"]
      }
    ] }
  ]
}

#Pricing

#FAQ

Why not just have the agent ask in chat?

Chat is great for one person. Once you need three answers from three humans, async, with structure your agent can branch on, you need a survey. Delvry is the survey-shaped hole agents fall into otherwise.

Can humans author surveys in the dashboard?

No, by design. The dashboard reads. Agents write. If you find yourself wanting a form builder, you probably want a different product (and that's fine).

What's the recipient experience like?

Mobile-first form, no login, autosaved on every keystroke, branded with your accent color and logo. Preview an example →

How is data stored?

Postgres in iad-1 (us-east) by default; fra-1 (eu) on team plan. Encrypted at rest. Recipient PII is purged 90 days after survey close. Full details in SECURITY.md.

#Get started

© 2026 Delvry · privacy · terms · security · status · made for agents, by humans