> ## Documentation Index
> Fetch the complete documentation index at: https://www.pickfu.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Which PickFu integration should I use?

> Compare PickFu's web app, MCP server, CLI, and REST API to choose the right way to create surveys and collect consumer feedback — by hand or in code.

PickFu gives you four ways to create surveys, pull results, and build consumer feedback into your workflow — from clicking through the web app to calling the REST API. The **MCP server** is the fastest way to get started in code: it works with the AI assistants you already use.

<img className="block dark:hidden" src="https://mintcdn.com/pickfu/QJcxZCx_vR2qxODa/images/connectors-light.svg?fit=max&auto=format&n=QJcxZCx_vR2qxODa&q=85&s=74975028e774f5a4d4f3338fe6f06237" alt="However you work — the web app, an AI assistant via the MCP server, the CLI from scripts and agents, or the REST API from your own app — you reach the same PickFu panel of real people, who return votes and written explanations in minutes." noZoom width="1120" height="500" data-path="images/connectors-light.svg" />

<img className="hidden dark:block" src="https://mintcdn.com/pickfu/QJcxZCx_vR2qxODa/images/connectors-dark.svg?fit=max&auto=format&n=QJcxZCx_vR2qxODa&q=85&s=633ffeccb7a1002255ef582e96778aa5" alt="However you work — the web app, an AI assistant via the MCP server, the CLI from scripts and agents, or the REST API from your own app — you reach the same PickFu panel of real people, who return votes and written explanations in minutes." noZoom width="1120" height="500" data-path="images/connectors-dark.svg" />

## Which should I use?

Read the **Reach for it when** row first — it maps your situation to a tool. Everything below it is supporting detail.

|                        | **Web app**                                         | **MCP server**                                                         | **CLI**                                                        | **REST API**                                                                       |
| ---------------------- | --------------------------------------------------- | ---------------------------------------------------------------------- | -------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
| **Who it's for**       | Anyone — no code                                    | People working inside an AI assistant                                  | Developers, scripts, autonomous agents                         | Developers building integrations                                                   |
| **Reach for it when…** | You want to create or read a poll by hand, visually | You want to run research by *chatting* with Claude, Cursor, or ChatGPT | You need polls in scripts, CI/CD, or a `watch` loop for agents | You're embedding PickFu in your own app, backend, or a no-code tool (Zapier, Make) |
| **How you use it**     | Open [app.pickfu.com](https://app.pickfu.com)       | Ask your AI assistant                                                  | `pickfu survey create …` in a terminal                         | HTTP requests to `api.pickfu.com/v1`                                               |
| **Getting started**    | Just sign in — nothing to install                   | [Connect once](/docs/integrations/mcp-server) (\~1 min) · OAuth or API key  | `npm i -g @pickfu/cli` · OAuth or API key                      | [Create an API key](https://app.pickfu.com/settings/api-keys)                      |
| **Output**             | Visual dashboard                                    | Rich chat — text + inline images                                       | JSON + readable tables                                         | JSON (OpenAPI-spec'd)                                                              |

<Tip>
  **Start with the web app** if you just want results. **Add the MCP server** to drive PickFu from the AI assistant you already use. **Reach for the CLI** when you need automation or agents. **Call the REST API** when PickFu lives inside your own product.
</Tip>

<CardGroup cols={3}>
  <Card title="MCP server" icon="robot" href="/docs/integrations/mcp-server">
    Connect Claude, Cursor, ChatGPT, Notion, Windsurf, and other AI assistants to PickFu.
  </Card>

  <Card title="CLI" icon="terminal" href="/docs/integrations/cli">
    Create and manage polls from the command line.
  </Card>

  <Card title="REST API" icon="code" href="/docs/api-reference/introduction">
    Call PickFu's v1 endpoints directly from any language.
  </Card>

  <Card title="Authentication" icon="key" href="/docs/authentication">
    OAuth and API key authentication for the MCP server, CLI, and API.
  </Card>

  <Card title="Support" icon="envelope" href="mailto:support@pickfu.com">
    Get help from our support team.
  </Card>
</CardGroup>

## What you can do

With the PickFu MCP server, CLI, and REST API, you can:

* **Create surveys from AI assistants** — Ask Claude, Cursor, or ChatGPT to create and publish PickFu polls through natural conversation
* **Generate and upload media** — Create images from prompts or upload your own for use in polls
* **Retrieve real-time results** — Get survey responses, AI summaries, and analytics as they come in
* **Target specific audiences** — Use demographic traits to reach the right respondents
* **Automate your workflow** — Integrate PickFu into your product development pipeline

## Still choosing between MCP and CLI?

These two are the closest substitutes — both let AI tools drive PickFu over the same platform. If you've narrowed it down to these two, here's where they actually differ:

| Capability                                                     | MCP server | CLI |
| -------------------------------------------------------------- | :--------: | :-: |
| View survey and generated images inline (in AI assistant chat) |     Yes    |  –  |
| Poll URL builder                                               |     Yes    |  –  |
| Help center search                                             |     Yes    |  –  |
| Watch/wait for survey completion (`survey watch`)              |      –     | Yes |
| Upload media from a local file                                 |      –     | Yes |
| JSON output for scripting                                      |      –     | Yes |
| Schema introspection                                           |      –     | Yes |

Everything else is shared: both create, update, publish, stop, and delete surveys; add respondents; read responses with demographics; generate images and upload media by URL; and manage tags, projects, and playbooks.

<Tip>
  **Use the MCP server** for conversational AI assistants like Claude, Cursor, and ChatGPT.

  **Use the CLI** for scripts, CI/CD pipelines, when Claude Code needs `survey watch` for blocking loops, or when agentic AI tools with terminal access ([OpenClaw](/docs/integrations/openclaw), Devin) need local file uploads or lower token usage. The CLI is more efficient for fully autonomous workflows.
</Tip>

## Getting started

<Steps>
  <Step title="Connect the MCP server">
    Add PickFu to your AI client — [setup takes about a minute](/docs/integrations/mcp-server). The MCP server works with Claude, Cursor, ChatGPT, Notion, Windsurf, and any MCP-compatible client.
  </Step>

  <Step title="Authenticate">
    Choose your auth method: **OAuth** (automatic — sign in when prompted) or **API key** (create at [Settings > API Keys](https://app.pickfu.com/settings/api-keys) for automation and CI/CD). Both work with the MCP server and CLI.
  </Step>

  <Step title="Create your first poll">
    Ask your AI assistant to create a PickFu poll, or use the [CLI](/docs/integrations/cli) to launch one from your terminal.
  </Step>
</Steps>