# Telnyx L2 · Gets in

Telnyx sells phone, messaging, email and AI services through an API.

**Can an AI agent use Telnyx? Yes, on its own.** Our agent got into Telnyx on its own in under a minute.

Category: SMS and voice · Connects by: MCP, API, CLI, SDK · Agent payments: UCP · Driven: 1 Nov 2026

**How to connect**
- MCP server URL: `https://api.telnyx.com/v2/mcp` (streamable HTTP, documented). Source: https://api.telnyx.com/v2/mcp
- API base URL: `https://api.telnyx.com/v2` (documented). Source: https://telnyx.com/openapi.json
- CLI install: `npm install -g @telnyx/agent-cli` (documented). Source: https://telnyx.com/llms.txt

**Level 2: Gets in.** An agent gets in on its own but does less than half the core work.
- Got in by: Sign-up by API (Under a minute)
- Got as far as: Pay: reaches the checkout (An agent payment for part of its API, none made yet)
- To reach L3: Let a trial or free plan reach the core features.

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**: On its own. Docs it can act on: llms.txt, an OpenAPI and an MCP server. (596 doc pages read)
2. **Get in**: On its own. Key by API. No key needed: stopped by a bot check; Email and password: stopped by robots.txt. (<1 minute)
3. **Use**: Not reached. Work not reached.
4. **Pay**: Reaches the checkout. An agent payment for part of its API, none made yet. (1 way for agents to pay)
5. **Leave**: On its own. Nothing to cancel; deletes its data, but the login stays.

## Getting in

1 of 11 ways in worked without a person.

The way that worked: **Sign-up by API**, under a minute. Needs an inbox. No 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 a first task. The core work wasn't measured in this drive.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does a first task. The core work wasn't measured in this drive.
- Signed agent: Not checked. Not checked: its robots.txt asks crawlers to stay off the sign-up page.

| Way in | What happened |
|---|---|
| Sign-up by API | Worked |
| No key needed | Stopped by a bot check |
| Pay per call | Not reached |
| Email and password | Stopped by robots.txt |
| Sign-in for apps (OAuth, MCP) | Stopped by robots.txt |
| Try first, claim later | Not tried: The same as another way |
| Registration through auth.md | Not tried: The same as another way |
| Email link | Not tried: Not part of this drive |
| Continue with Google | Not tried: Not part of this drive |
| Continue with Microsoft | Not tried: Not part of this drive |
| A key from a person | Not tried: Needs a person's account |

- Bot check: **Telnyx bot_challenge (first-party LLM reverse-CAPTCHA over the API) 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** “L NOT DISPUTE THE ENFORCEABILITY OF THIS AGREEMENT OR ANY RELATED REGISTRATION, CONSENT, ORDER, OR INSTRUCTION ON THE BASIS THAT IT WAS INITIATED OR ACCEPTED BY AN AUTOMATED AGENT RATHER THAN A HUMAN.” [Terms. Read on 1 Nov 2026.](https://telnyx.com/terms-and-conditions-of-service) **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 Telnyx

Both core tasks done, and 4 of 8 others.

- Reliability: core tasks that worked on all 3 runs: 83 of 100
- Handles mistakes: clear errors, retries without duplicates, honest limits: 68 of 100
- Surface tested: documented routes, tools and commands run and checked: 7 of 100
- Docs accuracy: documented operations that behaved as the docs say: 73 of 100
- Docs completeness: how fully the docs describe each operation: 74 of 100

Core tasks:

| Task | Result | Done through | Tried, not done | Offered, not tried |
|---|---|---|---|---|
| Make and control an outbound/inbound call | Done | API | – | MCP, CLI |
| Search and buy a phone number | Done | API, CLI | – | MCP |
| Send an SMS | Paid plan | – | API | MCP, CLI |
| Send a transactional email | Paid plan | – | API | MCP, CLI |
| Verify a user with an OTP (SMS, voice, flash call) | Paid plan | – | API | MCP |
| Deploy a Voice AI agent to answer or make calls | Paid plan | – | API | MCP |
| Call an open-weight LLM through the Inference API | Paid plan | – | API | MCP |
| Send a WhatsApp message | Paid plan: New accounts are restricted or have no funds; upgrading is in the portal. | – | API | MCP |

4 of 8 other tasks done:

- Record a call: Done
- Synthesize speech from text (TTS) for a call: Done
- Create text embeddings: Done
- Register a webhook for delivery/call events: Done
- Transcribe a call to text in real time: Partly
- Receive an inbound SMS or MMS: Paid plan
- Send an email from a template: Paid plan
- Schedule an email for later delivery: Paid plan
- Send a batch of up to 1,000 emails in one call: Paid plan
- Receive inbound email on a verified domain: Paid plan
- Add and verify a sending domain (SPF/DKIM/DMARC): Paid plan
- Track email opens and clicks: Paid plan
- Capture test emails in a sandbox without sending: Paid plan
- Port an existing number to Telnyx: Paid plan
- Register a 10DLC brand and campaign: Paid plan
- Look up a phone number's carrier, line type, and fraud signals: Paid plan
- Store a key-value pair with TTL: Paid plan
- Run a SQL query against a serverless edge database: Paid plan
- Provision an eSIM or IoT SIM for a connected device: Paid plan
- Set up branded caller ID / STIR-SHAKEN attestation: Paid plan
- Connect a Cloud VPN or virtual cross connect to the backbone: Paid plan
- Stream call audio in real time over WebSockets: Blocked
- Upload a file to object storage: Blocked
- Deploy a serverless function at the edge: Blocked

The plans they need:

- Verify a user with an OTP: Trial or higher
- Deploy a Voice AI agent: Trial or higher

Paid-plan tasks don't count toward the level. The drive used the Pretrial (free, no card) account from the bot signup.

What it can't do, and why:

- Send SMS, email, WhatsApp messages or one-time codes: New accounts are restricted or have no funds; upgrading is in the portal.
- Use AI chat models or Voice AI assistants with the account: Needs a higher account level than a new agent account gets.
- Use the MCP server: Keys from a new account are refused; the OAuth sign-in page is closed to AI agents.
- Fund the account or pay: Funding routes are refused at the new-account level; we had no wallet.
- Delete the account: The no delete route; the login still worked after clean-up.

**Surface audit:** 1598 documented operations, 257 run, 107 passed, 69 not as documented, 1186 blocked (sandbox or plan limits), 155 left out to stay safe.

## How an agent connects

MCP, API, OpenAPI, CLI, SDK, agent payments and llms.txt, all found.

Agent surfaces: API tested · MCP documented · CLI tested · SDK tested · Docs tested · Agent payments documented. Issues found: 73.

- **MCP server**: Listed, not tested. Official server. Remote, 6 tools in its server card. https://api.telnyx.com/v2/mcp (6 tools across its docs) 6 tools listed without signing in on 30 Oct 2026: `list_api_endpoints`, `get_api_endpoint_schema`, `invoke_api_endpoint`, `open_number_intelligence`, `open_usage_cost_explorer`, `open_voice_monitor`.
- **API**: 246 tested. REST v2, 1,510 operations in the OpenAPI spec. (1,512 operations across its docs)
- **OpenAPI**: Yes. 3.1.0, one file of 5 MB.
- **CLI**: 6 tested. @telnyx/agent-cli 0.4.2, @telnyx/cli 2.0.0, Go telnyx 0.24.0. (70 commands across its docs)
- **SDK**: All tested. telnyx (npm) 7.29.0. (1 method across its docs)
- **llms.txt**: Yes. https://telnyx.com/llms.txt
- **Agent payments**: Yes. UCP. The checkout: Plan and price: Pay as you go; Offers x402 payment.
- **Docs**: No gaps in what we read. Covers getting started, auth, error codes and code examples. 3 of 18 documented ways to do the core work worked when tried. (596 of 2,715 pages read)

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

## How Telnyx compares

On our standard (22 criteria, each against every product we measured on it):

- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **Ahead of most** 92 of 93 others lower, 1 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Ahead of most** 113 of 118 others lower, 5 the same.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Ahead of most** 111 of 141 others lower, 30 the same.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of most** 33 of 47 others lower, 14 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Ahead of most** 98 of 147 others lower, 49 the same.
- [All validation problems at once](https://agentdrives.com/standard#err-04): **Ahead of most** 24 of 35 others lower, 4 the same, 7 higher.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Level with most** 59 of 97 others the same, 38 lower.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **In the middle** 35 of 87 others lower, 42 the same, 10 higher.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with most** 80 of 105 others the same, 25 lower.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **In the middle** 56 of 144 others lower, 60 the same, 28 higher.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **In the middle** 40 of 104 others lower, 43 the same, 21 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with most** 71 of 85 others the same, 14 lower.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **In the middle** 56 of 145 others lower, 51 the same, 38 higher.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with most** 125 of 127 others the same, 2 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Level with most** 56 of 103 others the same, 24 lower, 23 higher.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **In the middle** 34 of 103 others lower, 29 the same, 40 higher.
- [Payments safe to retry, with a receipt](https://agentdrives.com/standard#pay-04): **Level with most** 13 of 23 others the same, 4 lower, 6 higher.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with most** 87 of 141 others the same, 10 lower, 44 higher.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with most** 87 of 141 others the same, 54 higher.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Behind most** 65 of 119 others higher, 54 the same.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Behind most** 62 of 85 others higher, 10 the same, 13 lower.
- [A person can claim what the agent made](https://agentdrives.com/standard#in-09): **Behind most** 6 of 9 others higher, 3 the same.

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

## For the team behind Telnyx

**9 things to fix for agents.**

Agent blockers: 3 found · Agent surfaces: 70 issues found. Safety review: no issues found.

Our agent got through Pay only in part, and didn't reach Use. Prove Telnyx 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: Not reached
- Pay: Partly
- Leave: Clear

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

## Where Telnyx fits

- Category: [Communication APIs](https://agentdrives.com/categories/communication?via=md), [SMS and voice](https://agentdrives.com/categories/sms-voice?via=md)
- Tasks: [Register a webhook](https://agentdrives.com/tasks/register-a-webhook), [Create text embeddings](https://agentdrives.com/tasks/create-text-embeddings)
- 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: [Cloudflare](https://agentdrives.com/vendors/cloudflare) (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), [x402](https://agentdrives.com/standards/x402) (pay per request), [MPP](https://agentdrives.com/standards/mpp) (machine payments)
- 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)

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