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

# Integrations overview

> How Hive connects to the tools you already run: OAuth connectors, MCP servers, signed incoming webhooks and Slack or Teams channels.

Hive works on top of the systems your team already uses. You connect a tool once, Hive reads
what you allow, and everything it notices or proposes stays tied to the source it came from.
Nothing is migrated: your data stays where it is, and Hive reads it in place.

Open **Integrations** in the sidebar. The screen has two tabs:

* **Connectors** — "Connectors let Hive read the tools you already run and carry out approved
  actions."
* **Channels** — "Ask Hive from Slack or Microsoft Teams. Signals and approvals stay in Hive."

## Four ways to connect

<CardGroup cols={2}>
  <Card title="Managed OAuth connectors" icon="key" href="/integrations/connect-an-app">
    Sign in to a provider such as Xero, HubSpot, Gmail or GitHub. Hive holds the credentials in
    its vault and starts read-only.
  </Card>

  <Card title="MCP servers" icon="server" href="/integrations/mcp-servers">
    Connect an official vendor MCP server (Notion, Linear, Sentry, Stripe) or any Model Context
    Protocol server by URL.
  </Card>

  <Card title="Incoming webhooks" icon="webhook" href="/integrations/incoming-webhooks">
    Let any system push signed JSON events into Hive, directly or through Zapier or Make.
  </Card>

  <Card title="Slack and Teams channels" icon="comments" href="/integrations/slack-and-teams">
    Ask Hive questions from Slack or Microsoft Teams with an @mention or a DM.
  </Card>
</CardGroup>

A connector brings data **in** and, with approval, carries actions **out** to that tool. A
channel is only a place to talk to Hive — it never delivers signals or approvals.

## What Hive does with a connected tool

Once a tool is connected, Hive uses it in several ways at once:

| Use | What happens |
| - | - |
| **Signals** | Certified source packs and monitoring plans watch the tool for work that is slipping — an overdue invoice, a stalled deal, an assigned issue nobody has touched in 14 days. See [Signals overview](/signals/overview). |
| **Ask Hive** | Ask can read live data from the tool on demand ("which invoices are overdue in Xero?") and cites what it read. See [Ask Hive](/ask/ask-hive). |
| **Business Brain** | Facts, entities and relationships from the tool feed the shared memory Hive answers from. File stores (Google Drive, OneDrive, SharePoint, Dropbox) sync into the knowledge base with their permissions. |
| **Actions** | Hive can prepare an action in the tool — send an email, create an invoice draft, move a deal stage — and hold it for your approval. |
| **Workflows and agents** | Workflow steps and Agent Studio agents use connected accounts to read and, with approval, write. |

## Read-first, by design

Every new account starts at the **Read** level: Hive can search and summarise, and nothing
leaves Hive. You can raise an account to **Draft** (Hive prepares actions and you approve them)
or **Act** (Hive carries out actions that policy has already approved). Today every write to a
connected tool is routed to human approval regardless of level. See
[Accounts and autonomy](/integrations/accounts-and-autonomy).

<Note>
  Connecting a tool never, on its own, gives Hive permission to change anything in it.
</Note>

## Who can connect what

* An **Owner** or **Admin** enables a provider for the workspace, simply by connecting it first.
* After that, **any member** can connect their own account of that provider. Before a provider
  is enabled, members see: "A workspace administrator must enable this provider before you can
  connect a personal account."
* Every connection belongs to the member who made it. Owners and Admins see a **Workspace
  connections** panel with metadata only — personal credentials, configuration, scopes, webhook
  URLs and actions stay private to their owner.
* Channels (Slack, Teams) and account autonomy levels are managed by Owners and Admins.

## How fresh the data is

* Right after you connect, Hive runs a first sync straight away.
* After that, Hive's always-on loop collects from every live connector **hourly**.
* Some providers also forward realtime events to Hive, which are picked up as they arrive.
* An Admin can press **Run loop now** on the Signals page or on the Connectors tab to refresh
  immediately.

## What is in the catalog

Hive's catalog covers accounting, payments, CRM, support, email, calendar, files, project
tracking and developer tools. The tiles you see depend on how your Hive workspace is
configured, and some providers are connect-only while their reads and actions are being built.
The full list, with what each provider supports today, is in the
[integrations catalog](/integrations/catalog).

## Build your own connector

If the tool you need is not in the catalog:

* If it has an **MCP server**, connect it by URL — see [MCP servers](/integrations/mcp-servers).
* If it can send webhooks (or you use Zapier or Make), point it at a signed
  [incoming webhook](/integrations/incoming-webhooks).

The **Built by me** filter on the Connectors tab shows the MCP servers and webhooks you created.

<Info>
  Hive does not offer customer API keys or outgoing webhooks today. See the
  [developer overview](/developers/overview) for what you can build against.
</Info>

## Related

<CardGroup cols={2}>
  <Card title="Connect an app" icon="plug" href="/integrations/connect-an-app">
    Step-by-step: connect your first tool.
  </Card>

  <Card title="Integrations catalog" icon="table-list" href="/integrations/catalog">
    Every provider and what it supports.
  </Card>

  <Card title="Health and disconnecting" icon="heart-pulse" href="/integrations/health-and-disconnect">
    Connection statuses and what disconnecting does.
  </Card>

  <Card title="Security overview" icon="shield-check" href="/security/overview">
    How credentials and data are protected.
  </Card>
</CardGroup>