> ## Documentation Index
> Fetch the complete documentation index at: https://docs.useagents.site/llms.txt
> Use this file to discover all available pages before exploring further.

# search_tools

> Use the `search_tools` MCP tool to find relevant developer tools from a natural-language query.

Use `search_tools` to query the UseAgents registry with a plain-language request. This helps your agent discover real tools instead of fabricating package names or relying on stale memory.

<Info>
  Requires an API key. Configure the `x-api-key` header when [connecting the
  MCP server](/mcp/connecting).
</Info>

## Parameters

| Parameter | Type   | Required | Description                                                                                        |
| --------- | ------ | -------- | -------------------------------------------------------------------------------------------------- |
| `q`       | string | Yes      | Natural-language query. Searches across tool names, descriptions, tags, languages, and categories. |

## Query guidance

Good queries usually include:

* The problem to solve
* The language or framework
* Important constraints such as deployment model or integration surface

Example queries:

* `authentication library for Node.js`
* `python sdk for Slack bots`
* `self-hosted feature flag service for Go`

## Returns

The tool returns results in **Toon** (Token-Oriented Object Notation), a compact, token-efficient format for LLM consumption. Learn more at [toonformat.dev](https://toonformat.dev).

Each result includes:

| Field         | Type           | Description                                                         |
| ------------- | -------------- | ------------------------------------------------------------------- |
| `name`        | string         | Tool name                                                           |
| `description` | string         | Full description of what the tool does                              |
| `languages`   | string\[]      | Supported languages                                                 |
| `frameworks`  | string\[]      | Supported frameworks                                                |
| `categories`  | string\[]      | Tool categories                                                     |
| `slug`        | string         | URL-friendly identifier for the tool                                |
| `updatedAt`   | string \| null | ISO timestamp when the tool was last updated; `null` if unavailable |

## Example call

```json theme={null}
{
  "q": "authentication library for Node.js"
}
```

Example response (Toon format):

```text theme={null}
results[1]:
  - name: Example Auth SDK
    description: A TypeScript authentication library for Node.js applications.
    languages[2]: TypeScript,JavaScript
    frameworks[1]: Next.js
    categories[2]: Authentication,SDK
    slug: example-auth-sdk
    updatedAt: 2026-07-23T12:00:00.000Z
```

## Use this tool when

* The agent needs to recommend a library, CLI, SDK, or API
* The agent should avoid fabricating or guessing tool names
* The agent needs accurate metadata before selecting a dependency

## Typical workflow

1. Call `search_tools` with a task-focused query.
2. Review the ranked results and metadata.
3. Use the returned links and descriptions to narrow the candidate set.
4. Only then recommend or integrate the selected tool.