How to configure and use AI Connectors for Deep Research

AI Connectors allow Benchling Deep Research to access data from external systems like Microsoft Teams, SharePoint, Slack, and other platforms that support the Model Context Protocol (MCP). This extends Deep Research's ability to provide comprehensive answers by incorporating information from multiple sources across your organization's data ecosystem. AI Connectors work by establishing secure connections between Benchling and external MCP servers, allowing Deep Research to retrieve relevant information while respecting your authentication and permissions in those systems.

Deep Research must be enabled on your tenant to use AI Connectors. To request that Benchling enable AI Connectors for your tenant, contact Benchling Support or your typical Benchling point of contact. 

Note: AI Connectors currently work with Deep Research only. Deep Research automatically determines which connected systems to query based on your prompt.

Configure AI Connectors

Before AI Connections are available for users to enable, tenant admins must first set up the AI Connector for the tenant. 

Set up a new connector

To configure an AI Connector:

1. In the left side bar, click Connections (the very last icon)
2. Click the AI Connectors tab
3. Click the expand icon to view the AI Connectors interface in full screen
4. Click the blue + icon to create a new connector
5. Complete the connector configuration:
   • Name: Enter a descriptive name for the connector (this is the name that will be visible to users)
   • Server: Enter the MCP server URL (typically ends in /mcp for HTTP connections or /sse for SSE connections)
   • Type: Select the connection type
     • [Default] Use HTTP for most connections (URLs ending in /mcp)
     • Use SSE for server-sent events connections (URLs ending in /sse)
     • If you're unsure, start with HTTP and try SSE if the connection doesn't work
6. Review the available tools from the MCP server and select which tools users can access
7. Click Save

For example, to connect to Microsoft Teams, you might enter https://teams.microsoft.com/mcp as the server URL and select HTTP as the type. To connect Deep Research in one tenant to another tenant, you can use the Benchling MCP url format like https://<tenant>.mcp.benchling.com/mcp

See Benchling MCP for more on setting up and using Benchling's MCP Server.

Manage tenant connectors

After creating a connector, admins can adjust settings or remove access. Note, the settings for admins to adjust the behavior for their tenant and to adjust the behavior for themselves as a user are both managed through this page. These settings will be present for tenant admins only:

• Admin settings: Adjust configuration settings for the connector for the entire tenant, including which tools are available to users
• [coming soon] Uninstall: Remove the connector for all users on the tenant

Set up AI Connectors as a user

After an admin configures an AI Connector, you can set up your personal connection to authenticate and select which tools you want to use.

Connect to an available connector

To set up your connection:

1. In the left-side menu, click Connections
2. Click the AI Connectors tab
3. Click the connector you want to use
4. In the pop-up window, click Authenticate or Connect
5. Complete authentication in the new tab or window that opens
6. Return to Benchling and finalize the connection
7. Select which tools you want to enable from the options the admin has made available
8. Click Save

Your selected connectors are now available to Deep Research. When you use Deep Research, it automatically determines whether to query your connected systems based on your prompt.

Manage your connections

You can adjust your AI Connector settings:

• Configuration: Adjust your personal settings, including which tools are enabled
• Toggle switch: Turn the connection on or off
• Disconnect: Remove the connector from your account entirely

FAQ and troubleshooting

What types of external systems can I connect?

You can connect to any system that provides an MCP server. Common examples include Microsoft Teams, SharePoint, Slack, and other collaboration or data platforms. The system must provide an MCP server URL for the connection.

Why am I getting an authentication error?

If you encounter authentication errors when setting up your connection, the external system may require pre-registration of the connection on the MCP server side. Benchling will support these pre-registered connections in the near future. Contact Benchling Support for assistance with authentication issues.

Which Benchling features work with AI Connectors?

AI Connectors currently work with Deep Research only. You cannot use AI Connectors with Ask or other AI features at this time.

Can I choose which connectors Deep Research uses for specific questions?

Not today. All connections you've enabled in the Connections app are available to Deep Research, which automatically determines which systems to query based on your prompt. You cannot enable or disable specific connections on a per-chat basis through the chat UI. Though you can return to the connections tab to enable or disable connections at any time. 

Do AI Connectors require additional licensing?

AI Connectors don't require additional licensing beyond your existing Benchling license. However, your tenant must have Deep Research enabled to use AI Connectors. Depending on the AI Connector, you may be required to have a license to the external system.