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

# Toolkit

> How CORE takes actions across your connected apps

## Taking actions across your apps

The Toolkit is CORE's hands. While the Agent thinks and Memory remembers, the Toolkit actually *does things* — creates issues, drafts emails, schedules meetings, sends messages — across all your connected apps.

You connect each app once. After that, every interface to CORE (WhatsApp, web dashboard, Claude Code, Cursor) can use those integrations. One connection, available everywhere.

**What a multi-step action looks like:** A user emails reporting a bug → CORE creates a Todoist task, spins up a Claude Code session with context from memory, writes a fix, and opens a PR. You come back to a summary and a link. One message, multiple tools, coordinated automatically.

***

## How It Works

### 1. You Connect Apps

From the [CORE Dashboard](https://app.getcore.me), connect the apps you use daily. Each integration authenticates via OAuth — no API keys to manage.

### 2. CORE Decides What to Use

When you ask CORE to do something, the Agent figures out which integration(s) to use:

```
You: "Create a GitHub issue for the auth bug and tell Sarah on Slack"

Agent:
→ Uses GitHub integration to create issue with context from memory
→ Uses Slack integration to DM Sarah with a link to the issue
```

### 3. Actions Execute with Context

Every action includes context from your memory. When CORE creates a Linear issue, it includes relevant discussion history. When it drafts an email, it knows your tone and past correspondence.

***

## What's Available

<CardGroup cols={2}>
  <Card title="Communication" icon="message">
    **Gmail** · **Slack** · **Discord** · **Zoho Mail**

    Send messages, draft emails, search conversations
  </Card>

  <Card title="Project Management" icon="list-check">
    **Linear** · **Todoist** · **Google Tasks**

    Create issues, update tasks, track progress
  </Card>

  <Card title="Development" icon="code">
    **GitHub** · **GitHub Analytics**

    Create issues, manage PRs, review code, track metrics
  </Card>

  <Card title="Calendar & Scheduling" icon="calendar">
    **Google Calendar** · **Cal.com**

    Schedule events, check availability, manage invites
  </Card>

  <Card title="Knowledge & Docs" icon="book">
    **Notion** · **Google Docs** · **Google Sheets**

    Search, create, and update documents and data
  </Card>

  <Card title="CRM" icon="users">
    **HubSpot**

    Manage contacts, deals, and customer data
  </Card>
</CardGroup>

See the [Toolkit documentation](/toolkit/overview) for detailed actions available per integration.

***

## How Toolkit Reaches Your AI Agents

Toolkit actions are exposed to AI agents through a single MCP endpoint. Instead of configuring separate MCP servers per app, you connect CORE once and any MCP-compatible agent (Claude Code, Cursor, Windsurf, etc.) gets the full toolkit with on-demand tool loading.

See the [Toolkit Overview](/toolkit/overview) for details on how on-demand tool loading works and MCP configuration.

***

## Next Steps

<CardGroup cols={3}>
  <Card title="Browse Integrations" icon="puzzle" href="/toolkit/overview">
    See all available integrations and their actions
  </Card>

  <Card title="MCP Configuration" icon="gear" href="/mcp/configuration">
    Configure which integrations to expose via MCP
  </Card>

  <Card title="Agent" icon="brain" href="/concepts/meta-agent">
    How the Agent decides which tools to use
  </Card>
</CardGroup>