Skip to main content
Connect your AI to the tools you already use.

How integrations work

EasyClaw uses the Model Context Protocol (MCP) to connect your AI assistant to external services. When you authorize an integration, a dedicated server is injected into your container, giving your AI access to that service’s API. Each integration runs as a separate server — one per service — for performance isolation. If one integration has an issue, it doesn’t affect the others.

Available integrations

Google Workspace

ServiceWhat your AI can do
GmailRead, search, and send emails
Google CalendarView schedule, create/edit events
Google DriveSearch and read files
Google DocsRead and create documents
Google SheetsRead and edit spreadsheets

Developer tools

ServiceWhat your AI can do
GitHubBrowse repos, read issues/PRs, create issues
LinearView and create issues, manage projects
NotionRead and create pages, query databases

Communication

ServiceWhat your AI can do
SlackRead and send messages in channels
TrelloView boards, create and move cards

And more

Over 250 integrations are available. If a service has an API, there’s likely an integration for it.

Setting up an integration

1

Go to settings

Open the EasyClaw web console and navigate to the Integrations page.
2

Choose a service

Select the service you want to connect (e.g., Google Calendar).
3

Authorize

Complete the OAuth flow — you’ll be redirected to the service’s login page to grant permission.
4

Done

The integration is injected into your container. Your AI can use it immediately.

OAuth and authentication

Integrations use OAuth for authentication. When you authorize a service:
  1. You’re redirected to the service’s OAuth consent screen
  2. You grant specific permissions (e.g., “read calendar events”)
  3. The OAuth token is stored securely
  4. The integration server in your container uses the token to make API calls on your behalf
You can revoke access to any integration at any time from the EasyClaw settings page.

Model Context Protocol (MCP)

MCP is an open standard for connecting AI models to external tools and data sources. It provides a structured way for AI assistants to discover available tools, understand parameters, and execute them. EasyClaw uses MCP as the bridge between ZeroClaw and external services. Each integration exposes its API as a set of MCP tools that the AI can call.
MCP is an open standard becoming the default for AI tool integration. By using MCP, EasyClaw ensures compatibility with a growing ecosystem of tools and services.