> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-tools/search-and-research/search-connected-apps.md).

# Search Connected Apps

Search connected services and retrieve content from the results. Use this tool when relevant information stays in an external service instead of a StackAI knowledge base.

## Use this tool

1. Configure **Connections** for the sources to search. For a user’s own account, configure **End-User Provider IDs** and ensure that the user connects the provider.
2. Use **Selected Connections** to narrow the configured connections when needed.
3. Enter **Search Query** and set **Max Results Per Source**. Run the tool.
4. Check **Results**, **Sources Searched**, and **Extraction Errors** before using the retrieved content.

## Behavior and limits

A successful search can still contain extraction errors for individual files. Sources Searched counts connections that were searched successfully; it is not a count of matching documents. Access depends on the accounts used for the selected connections.

**Inputs**

<table><thead><tr><th width="220">Parameter</th><th width="160">Type</th><th>Description</th></tr></thead><tbody><tr><td><code>Search Query</code> *</td><td>string</td><td>The search query to find relevant documents.</td></tr><tr><td><code>Max Results Per Source</code></td><td>integer</td><td>Maximum number of results to return per connection. Default: <code>2</code>.</td></tr></tbody></table>

**Configuration parameters**

<table><thead><tr><th width="220">Parameter</th><th width="160">Type</th><th>Description</th></tr></thead><tbody><tr><td><code>Connections</code></td><td>connection</td><td>The connections to search across.</td></tr><tr><td><code>End-User Provider IDs</code></td><td>array</td><td>Providers the end user connects with their own account.</td></tr><tr><td><code>Selected Connections</code></td><td>connection</td><td>Subset of connections to search (searches all if not set).</td></tr></tbody></table>

**Outputs**

<table><thead><tr><th width="220">Field</th><th width="160">Type</th><th>Description</th></tr></thead><tbody><tr><td><code>Results</code></td><td>object_array</td><td>The search results with extracted content.</td></tr><tr><td><code>Query</code></td><td>string</td><td>The search query that was used.</td></tr><tr><td><code>Sources Searched</code></td><td>number</td><td>Number of connections that were successfully searched.</td></tr><tr><td><code>Extraction Errors</code></td><td>string_array</td><td>Files that failed content extraction.</td></tr></tbody></table>

## Related guides

* [Indexed Search and Connected-App Search](https://docs.stackai.com/technical-reference/files-knowledge-and-retrieval/indexed-search-and-connected-app-search.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/stackai-tools/search-and-research/search-connected-apps.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
