> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/mcp-server/tools-and-support/tools/knowledge-bases.md).

# Knowledge Bases

Create and search Knowledge Bases, ingest content, and check indexing status.

Create and search Knowledge Bases, ingest content, and check indexing status.

See [plan access](broken://pages/GlhqboJgu5fTfPseY3y1#plan-access) and [query options](broken://pages/GlhqboJgu5fTfPseY3y1#query-options) for shared requirements.

## `list_knowledge_bases`

List all Knowledge Bases you have access to. Knowledge Bases store documents for semantic search.

**Returns:** Knowledge Base ID, name, workspace ID, status, and document count. Only Knowledge Bases with status `ready` can be searched.

| Parameter   | Values                               |
| ----------- | ------------------------------------ |
| **Filters** | workspace\_name, name, workspace\_id |
| **Sort**    | name, created\_at                    |

***

## `knowledge_base_manage`

Create or update a Knowledge Base. Omit `knowledge_base_id` to create a new Knowledge Base; provide it to update an existing one.

**Fields:** `knowledge_base_id`, `name`, `workspace_id`

**Required on create:** `name`, plus `workspace_id` when the user has access to multiple workspaces.

**Returns:** Knowledge Base ID, name, workspace ID, status, document count, and whether it was created.

***

## `search_knowledge_base`

Search a Knowledge Base for relevant content using semantic similarity.

**Requires:** `knowledge_base_id`, `query`

**Parameters:** `top_k` (number of results, 1-20, default 5)

**Returns:** Matching content ranked by relevance.

***

## `knowledge_base_create_direct_upload`

Start the two-step file upload flow for Knowledge Base ingestion. The tool returns a presigned upload URL, required headers, and a `signed_id`.

**Requires:** `knowledge_base_id`, `filename`, `content_type`, `byte_size`, `checksum`

**Returns:** `signed_id`, `upload_url`, and `upload_headers`.

***

## `knowledge_base_add_file`

Register an uploaded file with a Knowledge Base after `knowledge_base_create_direct_upload`. The document is queued for indexing.

**Requires:** `knowledge_base_id`, `signed_id`, `name`, `document_type`

**Optional fields:** `metadata`

**Returns:** Created document IDs and pending status.

***

## `knowledge_base_add_urls`

Bulk-ingest one or more web pages into a Knowledge Base. Each URL becomes a separate document and indexes asynchronously.

**Requires:** `knowledge_base_id`, `urls`

**Optional fields:** `metadata`

**Returns:** Created document IDs and pending status.

***

## `knowledge_base_get_status`

Get Knowledge Base indexing status and per-document statuses. Use this after adding files or URLs.

**Requires:** `knowledge_base_id`

**Optional fields:** `document_ids`, `cursor`, `items`

***

## `knowledge_base_get_document`

Get a Knowledge Base document by ID, including document metadata and extracted content when available.

**Requires:** `knowledge_base_id`, `document_id`

***

## `knowledge_base_update_document_metadata`

Replace a document's user-facing metadata. Metadata is a single-level key/value object and can be used in Knowledge Base search filters.

**Requires:** `knowledge_base_id`, `document_id`, `metadata`

***

## `knowledge_base_delete_document`

Permanently delete a single document from a Knowledge Base.

**Requires:** `knowledge_base_id`, `document_id`

{% hint style="warning" %}
This action cannot be undone. Confirm with the user before deleting a document.
{% endhint %}

***

## `knowledge_base_delete`

Permanently delete a Knowledge Base and all of its documents.

**Requires:** `knowledge_base_id`

{% hint style="warning" %}
This deletes the Knowledge Base, all documents, and underlying vectors. Confirm with the user before calling it.
{% endhint %}


---

# 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.airops.com/mcp-server/tools-and-support/tools/knowledge-bases.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.