canonical: https://jentic.com/apis/tcdial.com/tcdial

# TCDial API

Cloud telephony and call center API. The API exposes 21 endpoints secured with apiKey authentication.

## For AI agents

Programmatically initiate call, list calls. Covers 21 operations with apiKey authentication.

## Scope

Does not handle payments, crm, or developer tools - use for communications only.

## Capabilities

- Initiate call
- List calls
- Get call details
- End active call
- Create contact

## Use cases

### Communications Operations

Use the TCDial API to perform communications operations programmatically. The API provides 21 endpoints covering core functionality including initiate call, list calls, get call details.

Example prompt: Call POST /calls to initiate call

### Automated calls Management

Automate calls operations by combining multiple TCDial API endpoints. Agents can list calls and then get call details in a single workflow.

Example prompt: Call GET /calls to list calls, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call TCDial API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.

Example prompt: Search Jentic for 'initiate call', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/calls` | Initiate call |
| GET | `/calls` | List calls |
| GET | `/calls/{id}` | Get call details |
| POST | `/calls/{id}/end` | End active call |
| POST | `/contacts` | Create contact |
| GET | `/contacts` | List contacts |
| GET | `/contacts/{id}` | Get contact by ID |
| PUT | `/contacts/{id}` | Update contact |

## Key resources

- **calls** — Call management
- **contacts** — Contact management
- **campaigns** — Campaign management
- **agents** — Agent management
- **recordings** — Call recordings

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 64 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 76 / 100
  - Developer Experience & Jentic Compatibility: 56 / 100
  - AI-Readiness & Agent Experience: 49 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 100 / 100
- **View full report:** https://jentic.com/apis/tcdial.com/tcdial/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the TCDial API by hand means sending its X-API-Key header on every request, targeting the api.tcdial.com/v1 host, and building your own retry handling across call and contact endpoints. Through Jentic you install once, import the TCDial API from the API Directory, store the API key once, and your agent calls it.
- **Permission scoping:** The TCDial API puts the call and contact ids in the URL path (`/calls/{id}`, `/contacts/{id}`), so a rule can pin your agent to one call or contact: it can read and update those records. You choose the operations it may call, so actions like ending a call are not included unless you add them.
- **Credential handling:** Your TCDial API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'initiate a call' or 'update a contact', and Jentic returns the matching TCDial API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Twilio** — Alternative communications API
- **Sendgrid** — Alternative communications API
- **Pusher** — Complementary communications API

## FAQ

### What authentication does the TCDial API use?

The TCDial API uses an API key passed in the `X-API-Key` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I initiate call with the TCDial API?

Yes. Use the POST /calls endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the TCDial API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I initiate call through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'initiate call'. Jentic returns the matching TCDial API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the TCDial API have?

The TCDial API exposes 21 endpoints covering calls, contacts, campaigns operations.

### Can I limit what my agent is allowed to do with the TCDial API?

Yes. Because you run Jentic One yourself, your own rules decide which TCDial API operations and credentials the agent may use. The TCDial API carries the call and contact IDs in the URL path (`/calls/{id}`, `/contacts/{id}`), so you can pin the agent to a single call or contact and grant it only read and update access to those records. You choose the exact operations it may call, so an action like ending a call (POST `/calls/{id}/end`) stays off limits unless you explicitly add it.