# SurveyMonkey L4 · Runs on its own

SurveyMonkey is a forms product for making online surveys, with a REST API to create, edit, publish and read surveys and their responses.

**Can an AI agent use SurveyMonkey? Yes, in a browser.** Our agent got into SurveyMonkey on its own in 12 minutes and did 6 of its 7 core tasks.

Category: Forms · Connects by: MCP, API · Agent payments: None found · Driven: 28 Oct 2026

**How to connect**
- MCP server URL: `https://mcp.surveymonkey.com/mcp` (streamable HTTP, documented). Source: https://mcp.surveymonkey.com/mcp
- API base URL: `https://www.surveymonkey.com` (documented). Source: https://www.surveymonkey.com/openapi.json

**Level 4: Runs on its own.** An agent does the core work and can stop paying on its own.
- Got in by: Email and password (12 minutes, in a browser)
- Got as far as: Pay: reaches the checkout (Stopped at the €39 a month charge)
- To reach L5: Pay without a person.

1 drive, awaiting confirmation

[What the levels mean](https://agentdrives.com/method/levels?via=md)

## From finding it to leaving

What an agent managed without a person, at each step.

1. **Find**: Partly. Docs with gaps: llms.txt, an OpenAPI and an MCP server. (249 doc pages read)
2. **Get in**: On its own. Sign-up in a browser. Sign-in for apps (OAuth, MCP): stopped by a CAPTCHA. (12 minutes)
3. **Use**: On its own. Did: create, edit, copy and delete surveys through the API; publish and close a survey with a web link. (6 of 7 core tasks)
4. **Pay**: Reaches the checkout. Stopped at the €39 a month charge.
5. **Leave**: On its own. Nothing to cancel, deletes its account.

## Getting in

1 of 3 ways in worked without a person.

The way that worked: **Email and password**, 12 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): No. Stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does 6 of its 7 core tasks. Payment: reaches the checkout, stopped at the €39 a month charge.
- Signed agent (Known to Cloudflare): Yes. The sign-up page opens.

| Way in | What happened |
|---|---|
| Email and password | Worked |
| Sign-in for apps (OAuth, MCP) | Stopped by a CAPTCHA |
| Company single sign-on | Not tried: Not part of this drive |

- Crawlers: **robots.txt asks crawlers to stay off sign-up and the API.** Nothing to fix. It keeps these pages out of search and doesn't stop agents signing up.
- Bot check: **Auth0 username/password challenge let our agent through at sign up.** Our agent signs every request (Web Bot Auth).
- Terms: **Their terms say automated sign-up isn't allowed** “You may not register accounts using a disposable or temporary email address, “bots,” or other unauthorized automated methods.” [Acceptable use policy. Read on 28 Oct 2026.](https://www.surveymonkey.com/mp/legal/acceptable-uses-policy/) **To let agents sign up:** Allow accounts made by an agent that acts openly for an identified person or company.

[How agents get past bot checks](https://agentdrives.com/guides/let-signed-agents-past-your-bot-check.md?via=md)

## What an agent can do with SurveyMonkey

6 of 7 core tasks done, and 8 of 14 others.

- Reliability: core tasks that worked on all 3 runs: 71 of 100
- Handles mistakes: clear errors, retries without duplicates, honest limits: 55 of 100
- Surface tested: documented routes, tools and commands run and checked: 63 of 100
- Docs accuracy: documented operations that behaved as the docs say: 89 of 100
- Docs completeness: how fully the docs describe each operation: 79 of 100

Core tasks:

| Task | Result | Done through | Offered, not tried |
|---|---|---|---|
| Create a survey or form | Done | API | MCP |
| Edit a survey's questions | Done | API | MCP |
| Add conditional logic to a survey | Done | Web app | – |
| Publish or close a survey | Done | API | MCP |
| Share or distribute a survey via collectors (email, web link, SMS, QR) | Done | API | – |
| Read survey or form responses | Done | API | – |
| Analyse survey responses (sentiment, text analysis, AI) | Paid plan | – | MCP |
| Run a market research methodology (concept testing, MaxDiff, price optimization) | Paid plan | – | Web app |

8 of 14 other tasks done:

- Start a survey from a template: Done
- Export survey responses to a file: Done
- Duplicate a survey: Done
- Delete a survey: Done
- List surveys: Done
- Translate a survey into multiple languages: Done
- Save a partial survey response: Done
- Register an OAuth app / create an API key: Done
- Generate a survey with AI from a prompt: Partly
- Change account settings: Partly
- Get an AI summary or recommendation on results: Paid plan
- Set up response notification emails: Paid plan
- Restrict who can submit a survey (quotas, passcode): Paid plan
- Style a survey with custom themes and colors: Paid plan
- Invite a team member: Paid plan
- Set a team member's role or permissions: Paid plan
- Connect a third-party integration: Paid plan
- Configure SAML SSO: Paid plan
- Remove SurveyMonkey branding (white label): Paid plan
- Read collector traffic and response stats: Blocked
- Register a webhook: Blocked
- Buy respondents from the SurveyMonkey Audience panel: Not tried

The plans they need:

- Market research methodologies: paid add-on
- AI summary of results: paid
- Response notification emails: paid
- Response quotas: Advantage Annual
- Custom themes: Standard Monthly
- Roles: Team/Enterprise
- Integrations: paid
- SAML SSO: Enterprise
- White label: Premier Annual

Paid-plan tasks don't count toward the level. The drive used the free plan.

What it can't do, and why:

- Get an API key without a browser: Keys come only from the developer portal web page.
- Use the official MCP server: Its approval page shows an image puzzle to pick crosswalks.
- Set skip logic through the API: The public API has no logic fields; only the web builder sets it.
- Pay for a plan on its own: Checkout is a card form only; there is no agent payment option.
- Generate a survey with AI: The AI planner kept asking questions and never built the survey in three turns.

**Surface audit:** 158 documented operations, 94 run, 82 passed, 10 not as documented, 36 blocked (sandbox or plan limits), 28 left out to stay safe.

## How an agent connects

MCP, API, OpenAPI and llms.txt found.

Agent surfaces: API tested · MCP documented · CLI none found · SDK none found · Docs tested · Agent payments none found. Issues found: 14.

- **MCP server**: Listed, not tested. Official server. Remote server, OAuth only. Sign-in needed to see its tools. https://mcp.surveymonkey.com/mcp (1 tool across its docs)
- **API**: 92 tested. REST v3, about 150 documented operations on one reference page. (153 operations across its docs)
- **OpenAPI**: Yes. 3.2.0 file covers only the public pricing and sign-up pages, not the REST API.
- **CLI**: None found.
- **SDK**: None found.
- **llms.txt**: Yes. https://www.surveymonkey.com/llms.txt
- **Agent payments**: None found. The checkout: Reached the card form and stopped: Standard Monthly, €39 a month; Checkout: a Stripe card form; An invisible bot check loaded at checkout; Wallets: Google Pay, Link.
- **Docs**: Some gaps. Covers getting started and auth. Errors only mentioned in passing. No code examples. 4 of 9 documented ways to do the core work worked when tried. (249 of 902 pages read)

[The standards](https://agentdrives.com/standard)

## How SurveyMonkey compares

In Forms: 3rd of 4 Forms products our agent got into on its own.

- [Formbricks](https://agentdrives.com/tools/formbricks.md?via=md): L4, Gets in on its own
- [Tally](https://agentdrives.com/tools/tally.md?via=md): L4, Gets in on its own
- **SurveyMonkey** (this page): L4, Gets in on its own
- [Fillout](https://agentdrives.com/tools/fillout.md?via=md): L4, Gets in on its own
- [Formspree](https://agentdrives.com/tools/formspree.md?via=md): L1, Can't sign up on its own
- [Jotform](https://agentdrives.com/tools/jotform.md?via=md): L1, Can't sign up on its own
- [Typeform](https://agentdrives.com/tools/typeform.md?via=md): L1, Can't sign up on its own

[All 7 in Forms](https://agentdrives.com/categories/forms?via=md)

Sorted by level, then work done, then time to the first call. [How we rank](https://agentdrives.com/method?via=md#order)

On our standard (18 criteria: against other forms products where we measured 5 or more, otherwise against every product we measured):

- [A path written for agents](https://agentdrives.com/standard#docs-10): **The best result** All 4 others (forms products) lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Ahead of most** 81 of 103 others (every product) lower, 22 the same.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of most** 33 of 47 others (every product) lower, 14 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **Ahead of most** 64 of 103 others (every product) lower, 39 the same.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **In the middle** 2 of 4 others (forms products) lower, 2 the same.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with most** 61 of 85 others (every product) the same, 24 lower.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with most** 3 of 4 others (forms products) the same, 1 lower.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with most** 80 of 105 others (every product) the same, 25 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with most** 125 of 127 others (every product) the same, 2 lower.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **The same as all** 4 others (forms products).
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **Level with most** 91 of 93 others (every product) the same, 2 higher.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Level with most** 3 of 4 others (forms products) the same, 1 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with most** 84 of 118 others (every product) the same, 34 higher.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Behind most** 60 of 97 others (every product) higher, 28 the same, 9 lower.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Behind most** 65 of 104 others (every product) higher, 39 the same.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Behind most** 3 of 4 others (forms products) higher, 1 the same.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Behind most** 3 of 4 others (forms products) higher, 1 the same.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Behind most** 72 of 85 others (every product) higher, 10 the same, 3 lower.

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind SurveyMonkey

**8 things to fix for agents.**

Agent blockers: 3 found · Agent surfaces: 11 issues found. Safety review: no issues found.

Our agent got through Find and Pay only in part. Prove SurveyMonkey is yours, then see where each issue is, read your safety findings and ask for a free drive after a fix. How to fix each one comes with the Audit.

- Find: Partly
- Get in: Clear
- Use: Clear
- Pay: Partly
- Leave: Clear

[Claim SurveyMonkey, free](https://agentdrives.com/app/products?add=surveymonkey.com&ref=listing) · [What a drive covers](https://agentdrives.com/method?via=md)

## Where SurveyMonkey fits

- Category: [Marketing](https://agentdrives.com/categories/marketing?via=md), [Forms](https://agentdrives.com/categories/forms?via=md)
- Tasks: [Create a form](https://agentdrives.com/tasks/create-a-form), [Start from a template](https://agentdrives.com/tasks/start-from-a-template), [Register an OAuth app](https://agentdrives.com/tasks/register-an-oauth-app), [Add conditional logic to a form](https://agentdrives.com/tasks#add-conditional-logic-to-a-form), [Edit a form's questions](https://agentdrives.com/tasks#edit-a-form-s-questions), [Read form responses](https://agentdrives.com/tasks#read-form-responses)
- Wall: [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (our agent got in another way), [Terms that forbid agent accounts](https://agentdrives.com/findings/terms-against-agents?via=md) (our agent got in another way)
- Vendors: [Google reCAPTCHA](https://agentdrives.com/vendors/recaptcha) (on one way in)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [OpenAPI](https://agentdrives.com/standards/openapi) (its API, described), [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay), [Leave](https://agentdrives.com/access/leave)
- Rivals: [Fillout](https://agentdrives.com/tools/fillout?via=md) (L4), [Formbricks](https://agentdrives.com/tools/formbricks?via=md) (L4), [Tally](https://agentdrives.com/tools/tally?via=md) (L4)

## Cited in 1 article

- [CLI for AI agents: 11 of 14 databases have one](https://agentdrives.com/research/which-kinds-of-software-give-ai-agents-a-cli-or-mcp-server?via=md)

Data: [JSON](https://agentdrives.com/api/tools/surveymonkey.json?via=md) · [Markdown](https://agentdrives.com/tools/surveymonkey.md?via=md) · [History](https://agentdrives.com/tools/surveymonkey/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/surveymonkey.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/surveymonkey.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/surveymonkey?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).