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

# TasteDive API

TasteDive provides taste-based recommendations for music, movies, TV shows, podcasts, books, games, people, places, and brands. Single endpoint API that returns similar items based on input queries. The API exposes 1 endpoints secured with apiKey authentication.

## For AI agents

Programmatically get similar recommendations. Covers 1 operations with apiKey authentication.

## Scope

Does not handle payments, communications, or crm - use for maps and geolocation only.

## Capabilities

- Get similar recommendations
- Manage maps geolocation data programmatically
- Integrate TasteDive API into automated workflows
- Query and filter TasteDive API records by parameters
- Monitor TasteDive API operational status and events

## Use cases

### Maps and Geolocation Operations

Use the TasteDive API to perform maps geolocation operations programmatically. The API provides 1 endpoints covering core functionality including get similar recommendations.

Example prompt: Call GET /similar to get similar recommendations

### Data Retrieval and Monitoring

Query TasteDive API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.

Example prompt: Poll the primary TasteDive API endpoint, compare response to last known state, and alert if changed

### AI Agent Integration via Jentic

AI agents discover and call TasteDive 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 'get similar recommendations', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/similar` | Get similar recommendations |

## Key resources

- **Similar** — Operations for similar

## 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:** 48 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 50 / 100
  - Agent Usability: 94 / 100
  - Security: 15 / 100
  - AI Discoverability: 63 / 100
- **View full report:** https://jentic.com/apis/tastedive.com/tastedive/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 TasteDive API by hand means passing your key as the k query parameter, targeting the tastedive.com/api host, and building your own retry handling around its single similar-items endpoint. Through Jentic you install once, import the TasteDive API from the API Directory, store the access key once, and your agent calls it.
- **Permission scoping:** The TasteDive API exposes a single read endpoint where the query travels as request parameters, so limit the agent to the operation it needs, namely getting similar recommendations. You choose what it may call, and this endpoint only reads recommendations, so nothing else is included.
- **Credential handling:** Your TasteDive access 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 'get similar recommendations for a movie', and Jentic returns the matching TasteDive API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Here** — Alternative maps geolocation API
- **Tomtom** — Alternative maps geolocation API
- **Googleapis** — Complementary maps geolocation API

## FAQ

### What authentication does the TasteDive API use?

The TasteDive API uses an API key passed in the `k` query. 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 get similar recommendations with the TasteDive API?

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

### What are the rate limits for the TasteDive 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 get similar recommendations through Jentic?

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

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

The TasteDive API exposes 1 endpoints covering similar operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which TasteDive operations and credentials the agent may use. The TasteDive API exposes a single read-only endpoint, GET /similar, so you can restrict the agent to just getting similar recommendations and nothing else. That operation only reads recommendation data using your access key, which stays encrypted in your own instance, so the agent cannot write, delete, or reach any other service.