# Typeform for AI agents. Make the right form easier to review.

> Read accessible forms and related records in Typeform. Prepare a source-grounded response review briefing within the selected account.

- Page: https://www.agent200.com/connectors/typeform/
- Category: Search and data
- Authentication: Managed OAuth
- Identifier in code: `typeform`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Typeform, through Agent200. In code: "typeform".
What it does: Read accessible forms and related records in Typeform. Prepare a source-grounded response review briefing within the selected account.
Page: https://www.agent200.com/connectors/typeform/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Typeform's own page, through the authorization link Agent200 returns. Never ask a user for a Typeform password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: typeform_list_forms, typeform_get_form, typeform_list_responses, typeform_list_workspaces. Name "typeform" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/typeform/framework/claude/
   https://www.agent200.com/connectors/typeform/framework/chatgpt/
   https://www.agent200.com/connectors/typeform/framework/claude-code/
   https://www.agent200.com/connectors/typeform/framework/muse/
   https://www.agent200.com/connectors/typeform/framework/grok-bot/
   https://www.agent200.com/connectors/typeform/framework/openai-dots/
   https://www.agent200.com/connectors/typeform/framework/claude-duet/
   https://www.agent200.com/connectors/typeform/framework/hermes-agent/
   https://www.agent200.com/connectors/typeform/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Typeform connector, your agent reads forms and responses in each user's own Typeform account. It can list forms and workspaces, read a form, and list its responses, using only the tools your project allows.

Typeform is an online form builder for surveys, quizzes and questionnaires.

## Typeform tools

- **List forms** (`typeform_list_forms`, read): Find forms available to the connected user.
- **Read a form** (`typeform_get_form`, read): Retrieve the structure of one identified form.
- **List responses** (`typeform_list_responses`, read): Read submitted responses for a selected form.
- **List workspaces** (`typeform_list_workspaces`, read): Find accessible workspaces.

## Limits you can set

**Turn single tools on or off.** Let the agent read forms and responses, and switch off `typeform_list_responses` if it should only see form structure.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example forms and workspaces but not responses. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Typeform

Each end user authorizes their own Typeform account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Typeform account, once.
const connection = await agent200
  .user("user_123")
  .connect("typeform");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Typeform tools

Name the user, the model and the tools. The model decides which Typeform tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "List the forms in my Typeform account",
    tools: ["typeform"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Connect the intended account.** Use the documented Typeform authorization route. Confirm the organization, team or workspace before reading records.

**Match access to the request.** Authorize the intended Typeform account with forms:read and responses:read as needed. Responses may contain personal information.

**Preserve the application user.** Keep the same stable application user identity for connection and later requests. Store the Agent200 key outside prompts and code.

## Example requests

- "List the forms in my Typeform account"
- "Summarize the responses to the customer survey"
- "Show the questions on the signup form"

## Guides: Typeform with your AI framework

- [Typeform + Claude](https://www.agent200.com/connectors/typeform/framework/claude.md): Read forms with Claude and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.
- [Typeform + ChatGPT](https://www.agent200.com/connectors/typeform/framework/chatgpt.md): Use ChatGPT to build a separate read-only Typeform assistant with Agent200. Ground the response review briefing in returned source data.
- [Typeform + Claude Code](https://www.agent200.com/connectors/typeform/framework/claude-code.md): Use Claude Code to build a separate read-only Typeform assistant with Agent200. Ground the response review briefing in returned source data.
- [Typeform + Muse](https://www.agent200.com/connectors/typeform/framework/muse.md): Read forms with Muse and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.
- [Typeform + Grok Bot](https://www.agent200.com/connectors/typeform/framework/grok-bot.md): Read forms with Grok Bot and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.
- [Typeform + OpenAI Dots](https://www.agent200.com/connectors/typeform/framework/openai-dots.md): Use OpenAI Dots to build a separate read-only Typeform assistant with Agent200. Ground the response review briefing in returned source data.
- [Typeform + Claude Duet](https://www.agent200.com/connectors/typeform/framework/claude-duet.md): Read forms with Claude Duet and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.
- [Typeform + Hermes Agent](https://www.agent200.com/connectors/typeform/framework/hermes-agent.md): Read forms with Hermes Agent and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.
- [Typeform + OpenClaw](https://www.agent200.com/connectors/typeform/framework/openclaw.md): Read forms with OpenClaw and Agent200. Prepare a response review briefing using the connected user’s own Typeform account.

## FAQ

### What access does Typeform need?

Authorize the intended Typeform account with forms:read and responses:read as needed. Responses may contain personal information. [Provider documentation](https://developer.typeform.com/developers/get-started/scopes/).

### Does a list include every record?

Use a specified form ID, date range and pagination. A response list is not an aggregate unless all relevant pages and filters are accounted for.

### Can this workflow make changes?

The listed Typeform operations are read-only. A proposed change in the agent answer does not edit the source.

### How should I verify the answer?

Identify the selected form and compare the answer with form identity, questions, response IDs and answers. Disclose missing or inaccessible fields.

### Are these exact runtime tool schemas?

The listed identifiers describe catalogue capabilities. Discover the actual runtime tool names and input schemas before executing a request.

## Related connectors

- [Tavily](https://www.agent200.com/connectors/tavily.md): Web search built for agents, reached with your Agent200 API key.
- [Exa](https://www.agent200.com/connectors/exa.md): Search the web by meaning, read page contents and find similar pages, reached with your Agent200 API key.
- [Firecrawl](https://www.agent200.com/connectors/firecrawl.md): Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key.
- [Brave Search](https://www.agent200.com/connectors/brave-search.md): Search the web, news, images and videos from Brave's independent index, reached with your Agent200 API key.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
