Overview

Overview of connectors in MeinGPT

Connectors extend the capabilities of your chats and AI assistants by enabling them to interact with external systems and data sources.

What are connectors?

Connectors are standardized interfaces that allow AI models to:

  • Retrieve external data - Real-time information from various sources
  • Execute actions - Perform tasks in connected systems
  • Extend context - Relevant information for better responses
  • Automate workflows - Orchestrate complex processes

Available connectors

All connectors at a glance, grouped by use case:

Productivity & knowledge management

  • Google Workspace - Gmail, Calendar, and Drive as standalone connectors, running in user context
  • Asana - Tasks, projects, and workspaces via the official Asana MCP server
  • Atlassian - Jira, Confluence, and Compass via the Atlassian Rovo MCP server
  • Freshservice - Read tickets, requesters, assets, and solution articles, and update tickets, replies, and notes

Microsoft

CRM & sales

  • HubSpot - Contacts, companies, deals, and tickets via the HubSpot MCP server
  • Salesforce - Query CRM data (leads, opportunities, accounts), manage records, run SOQL/SOSL queries

DevOps

  • GitHub - Repositories, issues, and pull requests
  • Linear - Issue tracking and project management
  • Sentry - Retrieve error reports, manage DSNs, run autofix (beta)

Finance

  • Stripe - Manage customers, payments, subscriptions, and invoices
  • PayPal - Create invoices, process payments, generate reports

Meetings

  • tl;dv - Search meeting recordings and transcripts

Databases

  • MCP Database - Direct SQL queries against PostgreSQL, MySQL, or Microsoft SQL Server

Documentation

  • Context7 - Current documentation and code examples for libraries and frameworks

Native connector vs. data pool

The same architecture pattern applies to Microsoft 365, Google Workspace, and Atlassian:

  • Native connector: executes in user context with user-level permissions
  • Data pool (RAG): scalable retrieval on indexed datasets

Important: in data-pool setups, native user-level permissions from the source platform do not carry over automatically. Details are documented under "Large-scale search via data pools" on the relevant connector page and under Data Pools (RAG).

Built-in tools in Chats

Core built-in tools are now documented in the Chats section:

Enabling connectors

From the chat

As soon as the AI needs a connector in a conversation that your account isn't connected to yet, you can connect it right in the chat – no detour through the settings.

The AI shows a prompt with a Connect button (e.g. "Connect to Gmail", "Connect to Google Calendar", Asana, Confluence).

You authorize your account via OAuth in the window that opens.

After connecting, the AI continues the task automatically – without leaving the chat.

Connected services remain centrally manageable under Settings → Connections (disconnect, reconnect).

In the chat via the @ menu

Already-connected connectors can be called up directly in the chat input by typing @ — same pattern as assistants and data sources.

Type @ in the chat input. A picker opens showing your connected connectors (e.g. Google Calendar, Microsoft Teams, custom MCP servers).

Select the connector you want. It is inserted as an @-mention in the message and activated for this chat.

Active connectors appear as chips below the input field — click the × on a chip to remove the connector again.

Note

The connector must already be connected under Settings → Connections or via the "+" menu → Connectors in the chat. Otherwise it won't appear in the @ picker. Per-function permissions (e.g. "read-only" on Outlook or Teams) are honored whether the connector is activated via the @ menu or the "+" menu.

In the Assistant Editor

Open the Assistant Editor

Navigate to the "Tools" section

Select desired connectors

Configure required parameters

Save the assistant

Custom MCP Servers

You can also integrate your own MCP servers:

Requirements

  • Publicly accessible URL
  • MCP protocol implementation
  • HTTPS encryption
  • Authentication (optional)

Setup

Create the server

Create it via the "Add a custom MCP server" tile (name + URL)

Add credentials

OAuth (if the server supports it) or an API key/token as a header

Set permissions

In the assistant editor

Details incl. troubleshooting: Custom MCP Server Integration

Security

Permission Model

  • Tool-Level - Which tools can the assistant use?
  • Operation-Level - Which actions are allowed?
  • Data-Level - Which data can be accessed?
  • User-Level - Who can use which tools?

Best Practices

Minimal permissions

Grant only necessary rights

Audit logging

Log all tool usage

Secure connections

Always use HTTPS/TLS

Secrets management

Store API keys securely

Rate limiting

Prevent abuse

Example prompts

There's no fixed assistant type such as "business intelligence" or "research assistant" – which connectors you combine in an assistant determines what it can do. A few concrete examples taken from the individual connector pages:

"How many opportunities are in the 'Negotiation' stage this month and what is their total value?" (Salesforce)
"What were our ten highest-revenue products last quarter?" (MCP Database)
"Show me the most recently active HubSpot contacts and summarize the latest activity for 'Example Ltd'" (HubSpot)

More examples are on each connector's own page under "Usage Examples".

Keeping an eye on usage

Prompt and cost breakdowns aren't part of connector configuration – they live in the admin area: the AI Cockpit shows prompts, active users, and – on usage-based plans – cost by user and model.

Troubleshooting

Common Issues

Tool not responding:

  • Check connection
  • Increase timeouts
  • Analyze logs

Tool works once, then stops working:

  • Send your next message in the same chat and try the tool call again – every new message rebuilds the tool connection, which often picks up a fresh authorization automatically if the previous one had expired.
  • If the call keeps failing, open the tool picker (@ in the message box) or go to Settings → Connections and reconnect the affected tool – its stored authorization (especially for OAuth) couldn't be refreshed automatically.
  • If the problem persists, contact support with the affected chat link.

Unexpected results:

  • Verify tool configuration
  • Validate permissions
  • Check input format

Further Information

Was this page helpful?