# Plunk L2 · Gets in

Plunk is an email service for sending and automating email.

**Can an AI agent use Plunk? Yes, without signing up.** Our agent got into Plunk on its own in 5 minutes and did 2 of its 7 core tasks.

Category: Email infrastructure · Connects by: MCP, API · Agent payments: None found · Driven: 27 Oct 2026

**How to connect**
- API base URL: `https://next-api.useplunk.com` (documented). Source: https://docs.useplunk.com/openapi.json
- Docs page: `https://docs.useplunk.com/` (tested in our drive). Source: https://docs.useplunk.com/

**Level 2: Gets in.** An agent gets in on its own but does less than half the core work.
- Got in by: Runs locally, no account (5 minutes, no account)
- Got as far as: Pay: reaches the checkout (Stopped at the card form)
- To reach L3: Do half of the core work (now 29%).

[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**: On its own. Docs it can act on: llms.txt, an OpenAPI and an MCP server. (176 doc pages read)
2. **Get in**: On its own. Runs locally, key by API, sign-up in a browser. (5 minutes)
3. **Use**: Partly. Did: manage contacts, custom fields and CSV imports; build segments and track events. Not done: send any email, template or campaign. (2 of 7 core tasks)
4. **Pay**: Reaches the checkout. Stopped at the card form.
5. **Leave**: On its own. Nothing to cancel, deletes its account.

## Getting in

3 of 3 ways in worked without a person.

The way that worked: **Runs locally, no account**, 5 minutes. No inbox, browser or person needed.

- Agent on a server (API, MCP, CLI): Partly. Signs up, confirms its email, gets an API key, makes its first API call and does 2 of its 7 core tasks, then stops: the rest needs a paid plan.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does 2 of its 7 core tasks, then stops: the rest needs a paid plan.
- Signed agent (Known to Cloudflare): Yes. The sign-up page opens.

| Way in | What happened |
|---|---|
| Runs locally, no account | Worked |
| Sign-up by API | Worked |
| Email and password | Worked |

## What an agent can do with Plunk

2 of 7 core tasks done, and 11 of 19 others.

- Reliability: core tasks that worked on all 3 runs: 92 of 100
- Handles mistakes: clear errors, retries without duplicates, honest limits: 65 of 100
- Surface tested: documented routes, tools and commands run and checked: 77 of 100
- Docs accuracy: documented operations that behaved as the docs say: 87 of 100
- Docs completeness: how fully the docs describe each operation: 69 of 100

Core tasks:

| Task | Result | Done through | Tried, not done |
|---|---|---|---|
| Build an email automation | Done | API, MCP | – |
| Add a contact to an automation | Done | API, MCP | – |
| Send a transactional email | Blocked | – | API |
| Send an email from a template | Blocked: Every send needs a sender domain verified by DNS records. | – | API |
| Draft an email campaign | Blocked | – | API |
| Schedule an email campaign | Blocked | – | API |
| Receive inbound email | Blocked: Needs a verified domain and an MX record. | – | API |

11 of 19 other tasks done:

- Validate an email address: Done
- Create a list and add contacts to it: Done
- Update a contact or subscriber: Done
- Delete a contact or subscriber: Done
- Import contacts from a CSV file: Done
- Track an event for a contact: Done
- Create a custom contact field: Done
- Create a segment: Done
- Manage suppressions (bounce and complaint handling): Done
- Create an API key: Done
- Read usage and quotas: Done
- Add and verify a sending domain: Partly
- Track email opens and clicks: Partly
- Register a webhook: Partly
- Translate the unsubscribe footer and contact-facing pages: Partly
- Self-host the platform on your own infrastructure: Partly
- Remove the product's branding from emails: Paid plan
- Set a spend limit: Paid plan
- Create an email template: Blocked. Every send needs a sender domain verified by DNS records.
- Read campaign performance: Blocked
- Set up a preference centre or unsubscribe page: Blocked

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

What it can't do, and why:

- Send any email, template or campaign: Every send needs a sender domain verified by DNS records.
- Receive inbound email: Needs a verified domain and an MX record.
- Pay for the paid plan: Only card checkout exists.
- Delete the account through documented API: The account is deleted in the dashboard only.

**Surface audit:** 169 documented operations, 133 run, 123 passed, 17 not as documented, 27 blocked (sandbox or plan limits), 9 left out to stay safe.

## How an agent connects

MCP, API, OpenAPI and llms.txt found.

Agent surfaces: API tested · MCP tested · CLI none found · SDK none found · Docs tested · Agent payments none found. Issues found: 19.

- **MCP server**: 37 tested. Official server. Stdio server @plunk/mcp 0.17.0, 42 tools. (45 tools across its docs)
- **API**: 90 tested. REST at next-api.useplunk.com, about 115 documented endpoints. (117 operations across its docs)
- **OpenAPI**: Yes. 3.1.0, 18 operations; workflows, domains and events are not in it.
- **CLI**: None found.
- **SDK**: None found.
- **llms.txt**: Yes. https://www.useplunk.com/llms.txt
- **Agent payments**: None found. The checkout: Reached the card form and stopped: Pay-as-you-go; Checkout: Stripe Checkout; An invisible bot check loaded at checkout; Wallets: Link.
- **Docs**: No gaps in what we read. Covers getting started, auth, error codes and code examples. 2 of 6 documented ways to do the core work worked when tried. https://docs.useplunk.com/ (176 of 177 pages read)

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

## Tips for agent builders

- Use sk_ for everything except POST /v1/track, which takes pk_.
- Check GET /domains/project/:projectId (or plunk_list_domains) before sending: without a verified domain every send, template and campaign returns 403.
- Workflow steps need a 'position'; UPDATE_CONTACT takes config.updates. Read the execution back: a bad config only fails at run time.
- Prefer the MCP server's plunk_add_workflow_steps and plunk_check_workflow: they validate before saving.
- Bulk contact jobs take {"mode":"ids","contactIds":[...]}.

## How Plunk compares

In Email infrastructure: 2nd of 2 Email infrastructure products our agent got into on its own.

- [AgentMail](https://agentdrives.com/tools/agentmail.md?via=md): L5, Gets in on its own
- **Plunk** (this page): L2, Gets in on its own
- [MailerSend](https://agentdrives.com/tools/mailersend.md?via=md): L1, Can't sign up on its own
- [Mailgun](https://agentdrives.com/tools/mailgun.md?via=md): L1, Can't sign up on its own
- [Mailtrap](https://agentdrives.com/tools/mailtrap.md?via=md): L1, Can't sign up on its own
- [Postmark](https://agentdrives.com/tools/postmarkapp.md?via=md): L1, Can't sign up on its own
- [Resend](https://agentdrives.com/tools/resend.md?via=md): L1, Can't sign up on its own
- [SendGrid](https://agentdrives.com/tools/sendgrid.md?via=md): L1, Can't sign up on its own

[All 8 in Email infrastructure](https://agentdrives.com/categories/email-infrastructure?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 email infrastructure products where we measured 5 or more, otherwise against every product we measured):

- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **The best result** All 5 others (email infrastructure products) lower.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Ahead of most** 4 of 5 others (email infrastructure products) lower, 1 the same.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Ahead of most** 3 of 5 others (email infrastructure products) lower, 2 the same.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Ahead of most** 3 of 5 others (email infrastructure products) lower, 2 the same.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **In the middle** 35 of 87 others (every product) lower, 42 the same, 10 higher.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with most** 61 of 85 others (every product) the same, 24 lower.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of most** 27 of 47 others (every product) lower, 5 the same, 15 higher.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **In the middle** 40 of 104 others (every product) lower, 43 the same, 21 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with most** 71 of 85 others (every product) the same, 14 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with most** 56 of 103 others (every product) the same, 24 lower, 23 higher.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **The same as all** 5 others (email infrastructure products).
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Level with most** 3 of 5 others (email infrastructure products) the same, 1 lower, 1 higher.
- [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.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **In the middle** 34 of 103 others (every product) lower, 29 the same, 40 higher.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Level with most** 3 of 5 others (email infrastructure products) the same, 2 higher.
- [A person can claim what the agent made](https://agentdrives.com/standard#in-09): **Behind most** 6 of 9 others (every product) higher, 3 the same.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Behind most** 3 of 4 others (email infrastructure products) higher, 1 the same.
- [Real status codes](https://agentdrives.com/standard#err-01): **Behind most** 126 of 127 others (every product) higher, 1 the same.

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

## For the team behind Plunk

**11 things to fix for agents.**

Agent blockers: 1 found · Agent surfaces: 18 issues found. Safety review: no issues found.

Our agent got through Use and Pay only in part. Prove Plunk 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: Clear
- Get in: Clear
- Use: Partly
- Pay: Partly
- Leave: Clear

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

## Where Plunk fits

- Category: [Communication APIs](https://agentdrives.com/categories/communication?via=md), [Email infrastructure](https://agentdrives.com/categories/email-infrastructure?via=md)
- Tasks: [Create an API key](https://agentdrives.com/tasks/create-an-api-key), [Import data from a file or another tool](https://agentdrives.com/tasks/import-data-from-a-file-or-another-tool), [Read usage and quotas](https://agentdrives.com/tasks/read-usage-and-quotas), [Build an email automation](https://agentdrives.com/tasks#build-an-email-automation), [Create a segment](https://agentdrives.com/tasks#create-a-segment), [Update a contact or subscriber](https://agentdrives.com/tasks#update-a-contact-or-subscriber)
- 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: [MailerSend](https://agentdrives.com/tools/mailersend?via=md) (L1), [Mailgun](https://agentdrives.com/tools/mailgun?via=md) (L1), [Mailtrap](https://agentdrives.com/tools/mailtrap?via=md) (L1)

## Cited in 2 articles

- [How to let AI agents sign up for your product](https://agentdrives.com/guides/let-ai-agents-sign-up?via=md)
- [Can AI agents sign up for software? We drove 185](https://agentdrives.com/research/can-ai-agents-sign-up?via=md)

Data: [JSON](https://agentdrives.com/api/tools/useplunk.json?via=md) · [Markdown](https://agentdrives.com/tools/useplunk.md?via=md) · [History](https://agentdrives.com/tools/useplunk/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/useplunk.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/useplunk.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/useplunk?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).